F# F# (pronounced eff sharp) is a strongly typed, multi-paradigm programming language that encompasses functional, imperative, and object-oriented programming techniques. F# is most often used as a cross-platform CLI language, but can also be used to generate JavaScript and GPU code. F# is developed by the F# Software Foundation, Microsoft and open contributors. An open source, cross-platform compiler for F# is available from the F# Software Foundation. F# is also a fully supported language in Visual Studio and Xamarin Studio. Other tools supporting F# development include Mono, MonoDevelop, SharpDevelop and WebSharper. F# originated from ML and has been influenced by OCaml, C#, Python, Haskell, Scala and Erlang.
F^3T Standard automatic methods for recognizing problematic code can be greatly improved via the incremental application of human+artificial expertise. In this approach, call $F^3T$, AI tools explore software to find commits that they guess is most problematic. Humans the apply their expertise to check that guess (perhaps resulting in the AI updating the support vectors within their SVM learner). We recommend this human+AI partnership, for several reasons. When a new domain is encountered, $F^3T$ can learn better ways to label which comments refer to real problems. Further, in studies with 9 open source software projects, $F^3T$’s incremental application of human+artificial intelligence is at least an order of magnitude cheaper to use than existing methods. Lastly, $F^3T$ is very effective. For the data sets explored here, when compared to standard methods, $F^3T$ improved $P_{opt}(20)$ and G-scores performance by 26\% and 48\% on median value.
F1 Score “F-Measure”
Fabrik We present Fabrik, an online neural network editor that provides tools to visualize, edit, and share neural networks from within a browser. Fabrik provides a simple and intuitive GUI to import neural networks written in popular deep learning frameworks such as Caffe, Keras, and TensorFlow, and allows users to interact with, build, and edit models via simple drag and drop. Fabrik is designed to be framework agnostic and support high interoperability, and can be used to export models back to any supported framework. Finally, it provides powerful collaborative features to enable users to iterate over model design remotely and at scale.
Facebook 20 Tasks
Facebook AI Research
Facebook Artificial Intelligence Researchers (FAIR) seek to understand and develop systems with human-level intelligence by advancing the longer-term academic problems surrounding AI. Our research covers the full spectrum of topics related to AI, and to deriving knowledge from data: theory, algorithms, applications, software infrastructure and hardware infrastructure. Long-term objectives of understanding intelligence and building intelligent machines are bold and ambitious, and we know that making significant progress towards AI can’t be done in isolation. That’s why we actively engage with the research community through publications, open source software, participation in technical conferences and workshops, and collaborations with colleagues in academia.
Human and Smart Machine Co-Learning with Brain Computer Interface
Faceted Classification A Faceted classification is a classification scheme used in organizing knowledge into a systematic order. A faceted classification uses semantic categories, either general or subject-specific, that are combined to create the full classification entry. Many library classification systems use a combination of a fixed, enumerative taxonomy of concepts with subordinate facets that further refine the topic. There are two primary types of classification used for information organization: enumerative and faceted. An enumerative classification contains a full set of entries for all concepts. A faceted classification system uses a set of semantically cohesive categories that are combined as needed to create an expression of a concept. In this way, the faceted classification is not limited to already defined concepts. While this makes the classification quite flexible, it also makes the resulting expression of topics complex. To the extent possible, facets represent ‘clearly defined, mutually exclusive, and collectively exhaustive aspects of a subject. The premise is that any subject or class can be analyzed into its component parts (i.e., its aspects, properties, or characteristics).’ Some commonly used general-purpose facets are time, place, and form.
Facetize There is a plethora of datasets in various formats which are usually stored in files, hosted in catalogs, or accessed through SPARQL endpoints. In most cases, these datasets cannot be straightforwardly explored by end users, for satisfying recall-oriented information needs. To fill this gap, in this paper we present the design and implementation of Facetize, an editor that allows users to transform (in an interactive manner) datasets, either static (i.e. stored in files), or dynamic (i.e. being the results of SPARQL queries), to datasets that can be directly explored effectively by themselves or other users. The latter (exploration) is achieved through the familiar interaction paradigm of Faceted Search (and Preference-enriched Faceted Search). Specifically in this paper we describe the requirements, we introduce the required set of transformations, and then we detail the functionality and the implementation of the editor Facetize that realizes these transformations. The supported operations cover a wide range of tasks (selection, visibility, deletions, edits, definition of hierarchies, intervals, derived attributes, and others) and Facetize enables the user to carry them out in a user-friendly and guided manner, without presupposing any technical background (regarding data representation or query languages). Finally we present the results of an evaluation with users. To the best of your knowledge, this is the first editor for this kind of tasks.
Facets Dive Dive is a tool for interactively exploring up to tens of thousands of multidimensional data points, allowing users to seamlessly switch between a high-level overview and low-level details. Each example is a represented as single item in the visualization and the points can be positioned by faceting/bucketing in multiple dimensions by their feature values. Combining smooth animation and zooming with faceting and filtering, Dive makes it easy to spot patterns and outliers in complex data sets.
Facets Overview Overview gives a high-level view of one or more data sets. It produces a visual feature-by-feature statistical analysis, and can also be used to compare statistics across two or more data sets. The tool can process both numeric and string features, including multiple instances of a number or string per feature.
Overview can help uncover issues with datasets, including the following:
• Unexpected feature values
• Missing feature values for a large number of examples
• Training/serving skew
• Training/test/validation set skew
Key aspects of the visualization are outlier detection and distribution comparison across multiple datasets. Interesting values (such as a high proportion of missing data, or very different distributions of a feature across multiple datasets) are highlighted in red. Features can be sorted by values of interest such as the number of missing values or the skew between the different datasets.
Fact Extraction and VERification
This paper describes a baseline for the second iteration of the Fact Extraction and VERification shared task (FEVER2.0) which explores the resilience of systems through adversarial evaluation. We present a collection of simple adversarial attacks against systems that participated in the first FEVER shared task. FEVER modeled the assessment of truthfulness of written claims as a joint information retrieval and natural language inference task using evidence from Wikipedia. A large number of participants made use of deep neural networks in their submissions to the shared task. The extent as to whether such models understand language has been the subject of a number of recent investigations and discussion in literature. In this paper, we present a simple method of generating entailment-preserving and entailment-altering perturbations of instances by common patterns within the training data. We find that a number of systems are greatly affected with absolute losses in classification accuracy of up to $29\%$ on the newly perturbed instances. Using these newly generated instances, we construct a sample submission for the FEVER2.0 shared task. Addressing these types of attacks will aid in building more robust fact-checking models, as well as suggest directions to expand the datasets.
FactChecker We present a novel natural language query interface, the FactChecker, aimed at text summaries of relational data sets. The tool focuses on natural language claims that translate into an SQL query and a claimed query result. Similar in spirit to a spell checker, the FactChecker marks up text passages that seem to be inconsistent with the actual data. At the heart of the system is a probabilistic model that reasons about the input document in a holistic fashion. Based on claim keywords and the document structure, it maps each text claim to a probability distribution over associated query translations. By efficiently executing tens to hundreds of thousands of candidate translations for a typical input document, the system maps text claims to correctness probabilities. This process becomes practical via a specialized processing backend, avoiding redundant work via query merging and result caching. Verification is an interactive process in which users are shown tentative results, enabling them to take corrective actions if necessary. Our system was tested on a set of 53 public articles containing 392 claims. Our test cases include articles from major newspapers, summaries of survey results, and Wikipedia articles. Our tool revealed erroneous claims in roughly a third of test cases. A detailed user study shows that users using our tool are in average six times faster at checking text summaries, compared to generic SQL interfaces. In fully automated verification, our tool achieves significantly higher recall and precision than baselines from the areas of natural language query interfaces and fact checking.
Factor Adjusted Robust Multiple Testing Large-scale multiple testing with correlated and heavy-tailed data arises in a wide range of research areas from genomics, medical imaging to finance. Conventional methods for estimating the false discovery proportion (FDP) often ignore the effect of heavy-tailedness and the dependence structure among test statistics, and thus may lead to inefficient or even inconsistent estimation. Also, the assumption of joint normality is often imposed, which is too stringent for many applications. To address these challenges, in this paper we propose a factoradjusted robust procedure for large-scale simultaneous inference with control of the false discovery proportion. We demonstrate that robust factor adjustments are extremely important in both improving the power of the tests and controlling FDP. We identify general conditions under which the proposed method produces consistent estimate of the FDP. As a byproduct that is of independent interest, we establish an exponential-type deviation inequality for a robust U-type covariance estimator under the spectral norm. Extensive numerical experiments demonstrate the advantage of the proposed method over several state-of-the-art methods especially when the data are generated from heavy-tailed distributions. Our proposed procedures are implemented in the R-package farmtest.
Factor Analysis Factor analysis is a statistical method used to describe variability among observed, correlated variables in terms of a potentially lower number of unobserved variables called factors. For example, it is possible that variations in four observed variables mainly reflect the variations in two unobserved variables. Factor analysis searches for such joint variations in response to unobserved latent variables. The observed variables are modelled as linear combinations of the potential factors, plus “error” terms. The information gained about the interdependencies between observed variables can be used later to reduce the set of variables in a dataset.
Factor analysis for INteraction
This article is motivated by the problem of inference on interactions among chemical exposures impacting human health outcomes. Chemicals often co-occur in the environment or in synthetic mixtures and as a result exposure levels can be highly correlated. We propose a latent factor joint model, which includes shared factors in both the predictor and response components while assuming conditional independence. By including a quadratic regression in the latent variables in the response component, we induce flexible dimension reduction in characterizing main effects and interactions. We propose a Bayesian approach to inference under this Factor analysis for INteractions (FIN) framework. Through appropriate modifications of the factor modeling structure, FIN can accommodate higher order interactions and multivariate outcomes. We provide theory on posterior consistency and the impact of misspecifying the number of factors. We evaluate the performance using a simulation study and data from the National Health and Nutrition Examination Survey (NHANES). Code is available on GitHub.
Factor Complex We introduce the factor complex of a neural code, and show how intervals and maximal codewords are captured by the combinatorics of factor complexes. We use these results to obtain algebraic and combinatorial characterizations of max-intersection-complete codes, as well as a new combinatorial characterization of intersection-complete codes.
Factor Graph A factor graph is a bipartite graph representing the factorization of a function. In probability theory and its applications, factor graphs are used to represent factorization of a probability distribution function, enabling efficient computations, such as the computation of marginal distributions through the sum-product algorithm. One of the important success stories of factor graphs and the sum-product algorithm is the decoding of capacity-approaching error-correcting codes, such as LDPC and turbo codes. Factor graphs generalize constraint graphs. A factor whose value is either 0 or 1 is called a constraint. A constraint graph is a factor graph where all factors are constraints. The max-product algorithm for factor graphs can be viewed as a generalization of the arc-consistency algorithm for constraint processing.
Factor-Augmented Markov Switching
This paper investigates the role of high-dimensional information sets in the context of Markov switching models with time varying transition probabilities. Markov switching models are commonly employed in empirical macroeconomic research and policy work. However, the information used to model the switching process is usually limited drastically to ensure stability of the model. Increasing the number of included variables to enlarge the information set might even result in decreasing precision of the model. Moreover, it is often not clear a priori which variables are actually relevant when it comes to informing the switching behavior. Building strongly on recent contributions in the field of dynamic factor analysis, we introduce a general type of Markov switching autoregressive models for non-linear time series analysis. Large numbers of time series are allowed to inform the switching process through a factor structure. This factor-augmented Markov switching (FAMS) model overcomes estimation issues that are likely to arise in previous assessments of the modeling framework. More accurate estimates of the switching behavior as well as improved model fit result. The performance of the FAMS model is illustrated in a simulated data example as well as in an US business cycle application.
FactorBase We describe FactorBase, a new SQL-based framework that leverages a relational database management system to support multi-relational model discovery. A multi-relational statistical model provides an integrated analysis of the heterogeneous and interdependent data resources in the database. We adopt the BayesStore design philosophy: statistical models are stored and managed as first-class citizens inside a database. Whereas previous systems like BayesStore support multi-relational inference, FactorBase supports multi-relational learning. A case study on six benchmark databases evaluates how our system supports a challenging machine learning application, namely learning a first-order Bayesian network model for an entire database. Model learning in this setting has to examine a large number of potential statistical associations across data tables. Our implementation shows how the SQL constructs in FactorBase facilitate the fast, modular, and reliable development of highly scalable model learning systems.
Factored Bandits We introduce the factored bandits model, which is a framework for learning with limited (bandit) feedback, where actions can be decomposed into a Cartesian product of atomic actions. Factored bandits incorporate rank-1 bandits as a special case, but significantly relax the assumptions on the form of the reward function. We provide an anytime algorithm for stochastic factored bandits and up to constants matching upper and lower regret bounds for the problem. Furthermore, we show that with a slight modification the proposed algorithm can be applied to utility based dueling bandits. We obtain an improvement in the additive terms of the regret bound compared to state of the art algorithms (the additive terms are dominating up to time horizons which are exponential in the number of arms).
Factorial Hidden Markov Models
We present a framework for learning in hidden Markov models with distributed state representations. Within this framework , we derive a learning algorithm based on the Expectation-Maximization (EM) procedure for maximum likelihood estimation. Analogous to the standard Baum-Welch update rules, the M-step of our algorithm is exact and can be solved analytically. However, due to the combinatorial nature of the hidden state representation, the exact E-step is intractable. A simple and tractable mean field approximation is derived. Empirical results on a set of problems suggest that both the mean field approximation and Gibbs sampling are viable alternatives to the computationally expensive exact algorithm.
Factorisation Autoencoder
Factorization Machine
In this paper, we introduce Factorization Machines (FM) which are a new model class that combines the advantages of Support Vector Machines (SVM) with factorization models. Like SVMs, FMs are a general predictor working with any real valued feature vector. In contrast to SVMs, FMs model all interactions between variables using factorized parameters. Thus they are able to estimate interactions even in problems with huge sparsity (like recommender systems) where SVMs fail. We show that the model equation of FMs can be calculated in linear time and thus FMs can be optimized directly. So unlike nonlinear SVMs, a transformation in the dual form is not necessary and the model parameters can be estimated directly without the need of any support vector in the solution. We show the relationship to SVMs and the advantages of FMs for parameter estimation in sparse settings. On the other hand there are many different factorization models like matrix factorization, parallel factor analysis or specialized models like SVD++, PITF or FPMC. The drawback of these models is that they are not applicable for general prediction tasks but work only with special input data. Furthermore their model equations and optimization algorithms are derived individually for each task. We show that FMs can mimic these models just by specifying the input data (i.e. the feature vectors). This makes FMs easily applicable even for users without expert knowledge in factorization models.
libFM: Factorization Machine Library
A Boosting Framework of Factorization Machine
Factorized Adversarial Network
In this paper, we propose Factorized Adversarial Networks (FAN) to solve unsupervised domain adaptation problems for image classification tasks. Our networks map the data distribution into a latent feature space, which is factorized into a domain-specific subspace that contains domain-specific characteristics and a task-specific subspace that retains category information, for both source and target domains, respectively. Unsupervised domain adaptation is achieved by adversarial training to minimize the discrepancy between the distributions of two task-specific subspaces from source and target domains. We demonstrate that the proposed approach outperforms state-of-the-art methods on multiple benchmark datasets used in the literature for unsupervised domain adaptation. Furthermore, we collect two real-world tagging datasets that are much larger than existing benchmark datasets, and get significant improvement upon baselines, proving the practical value of our approach.
Factorized Macro Action Reinforcement Learning One problem in the application of reinforcement learning to real-world problems is the curse of dimensionality on the action space. Macro actions, a sequence of primitive actions, have been studied to diminish the dimensionality of the action space with regard to the time axis. However, previous studies relied on humans defining macro actions or assumed macro actions as repetitions of the same primitive actions. We present Factorized Macro Action Reinforcement Learning (FaMARL) which autonomously learns disentangled factor representation of a sequence of actions to generate macro actions that can be directly applied to general reinforcement learning algorithms. FaMARL exhibits higher scores than other reinforcement learning algorithms on environments that require an extensive amount of search.
Fader Network This paper introduces a new encoder-decoder architecture that is trained to reconstruct images by disentangling the salient information of the image and the values of attributes directly in the latent space. As a result, after training, our model can generate different realistic versions of an input image by varying the attribute values. By using continuous attribute values, we can choose how much a specific attribute is perceivable in the generated image. This property could allow for applications where users can modify an image using sliding knobs, like faders on a mixing console, to change the facial expression of a portrait, or to update the color of some objects. Compared to the state-of-the-art which mostly relies on training adversarial networks in pixel space by altering attribute values at train time, our approach results in much simpler training schemes and nicely scales to multiple attributes. We present evidence that our model can significantly change the perceived value of the attributes while preserving the naturalness of images.
An Inutitive Understanding to Fader Networks
Failure Rate Failure rate is the frequency with which an engineered system or component fails, expressed, for example, in failures per hour. It is often denoted by the Greek letter lambda and is important in reliability engineering. The failure rate of a system usually depends on time, with the rate varying over the life cycle of the system. For example, an automobile’s failure rate in its fifth year of service may be many times greater than its failure rate during its first year of service. One does not expect to replace an exhaust pipe, overhaul the brakes, or have major transmission problems in a new vehicle. In practice, the mean time between failures (MTBF, 1/lambda) is often reported instead of the failure rate. This is valid and useful if the failure rate may be assumed constant – often used for complex units / systems, electronics – and is a general agreement in some reliability standards (Military and Aerospace). It does in this case only relate to the flat region of the bathtub curve, also called the ‘useful life period’. Because of this, it is incorrect to extrapolate MTBF to give an estimate of the service life time of a component, which will typically be much less than suggested by the MTBF due to the much higher failure rates in the ‘end-of-life wearout’ part of the ‘bathtub curve’. The reason for the preferred use for MTBF numbers is that the use of large positive numbers (such as 2000 hours) is more intuitive and easier to remember than very small numbers (such as 0.0005 per hour). The MTBF is an important system parameter in systems where failure rate needs to be managed, in particular for safety systems. The MTBF appears frequently in the engineering design requirements, and governs frequency of required system maintenance and inspections. In special processes called renewal processes, where the time to recover from failure can be neglected and the likelihood of failure remains constant with respect to time, the failure rate is simply the multiplicative inverse of the MTBF (1/lambda). A similar ratio used in the transport industries, especially in railways and trucking is ‘mean distance between failures’, a variation which attempts to correlate actual loaded distances to similar reliability needs and practices. Failure rates are important factors in the insurance, finance, commerce and regulatory industries and fundamental to the design of safe systems in a wide variety of applications.
Failure Time Analysis
Fair Forest The potential lack of fairness in the outputs of machine learning algorithms has recently gained attention both within the research community as well as in society more broadly. Surprisingly, there is no prior work developing tree-induction algorithms for building fair decision trees or fair random forests. These methods have widespread popularity as they are one of the few to be simultaneously interpretable, non-linear, and easy-to-use. In this paper we develop, to our knowledge, the first technique for the induction of fair decision trees. We show that our ‘Fair Forest’ retains the benefits of the tree-based approach, while providing both greater accuracy and fairness than other alternatives, for both ‘group fairness’ and ‘individual fairness.” We also introduce new measures for fairness which are able to handle multinomial and continues attributes as well as regression problems, as opposed to binary attributes and labels only. Finally, we demonstrate a new, more robust evaluation procedure for algorithms that considers the dataset in its entirety rather than only a specific protected attribute.
Fair on Average Causal Effect
As virtually all aspects of our lives are increasingly impacted by algorithmic decision making systems, it is incumbent upon us as a society to ensure such systems do not become instruments of unfair discrimination on the basis of gender, race, ethnicity, religion, etc. We consider the problem of determining whether the decisions made by such systems are discriminatory, through the lens of causal models. We introduce two definitions of group fairness grounded in causality: fair on average causal effect (FACE), and fair on average causal effect on the treated (FACT). We use the Rubin-Neyman potential outcomes framework for the analysis of cause-effect relationships to robustly estimate FACE and FACT. We demonstrate the effectiveness of our proposed approach on synthetic data. Our analyses of two real-world data sets, the Adult income data set from the UCI repository (with gender as the protected attribute), and the NYC Stop and Frisk data set (with race as the protected attribute), show that the evidence of discrimination obtained by FACE and FACT, or lack thereof, is often in agreement with the findings from other studies. We further show that FACT, being somewhat more nuanced compared to FACE, can yield findings of discrimination that differ from those obtained using FACE.
Fair on Average Causal Effect on the Treated
As virtually all aspects of our lives are increasingly impacted by algorithmic decision making systems, it is incumbent upon us as a society to ensure such systems do not become instruments of unfair discrimination on the basis of gender, race, ethnicity, religion, etc. We consider the problem of determining whether the decisions made by such systems are discriminatory, through the lens of causal models. We introduce two definitions of group fairness grounded in causality: fair on average causal effect (FACE), and fair on average causal effect on the treated (FACT). We use the Rubin-Neyman potential outcomes framework for the analysis of cause-effect relationships to robustly estimate FACE and FACT. We demonstrate the effectiveness of our proposed approach on synthetic data. Our analyses of two real-world data sets, the Adult income data set from the UCI repository (with gender as the protected attribute), and the NYC Stop and Frisk data set (with race as the protected attribute), show that the evidence of discrimination obtained by FACE and FACT, or lack thereof, is often in agreement with the findings from other studies. We further show that FACT, being somewhat more nuanced compared to FACE, can yield findings of discrimination that differ from those obtained using FACE.
Fair Top-k Ranking
We present a formal problem definition and an algorithm to solve the Fair Top-k Ranking problem. The problem consists of creating a ranking of k elements out of a pool of n >> k candidates. The objective is to maximize utility, and maximization is subject to a ranked group fairness constraint. Our definition of ranked group fairness uses the standard notion of protected group to extend the concept of group fairness. It ensures that every prefix of the rank contains a number of protected candidates that is statistically indistinguishable from a given target proportion, or exceeds it. The utility objective favors rankings in which every candidate included in the ranking is more qualified than any candidate not included, and rankings in which candidates are sorted by decreasing qualifications. We describe an efficient algorithm for this problem, which is tested on a series of existing datasets, as well as new datasets. Experimentally, this approach yields a ranking that is similar to the so-called ‘color-blind’ ranking, while respecting the fairness criteria. To the best of our knowledge, FA*IR is the first algorithm grounded in statistical tests that can be used to mitigate biases in ranking against an under-represented group.
Fairness-Aware Algorithm for Concurrent Service Selection
The increasing momentum of service-oriented architecture has led to the emergence of divergent delivered services, where service selection is meritedly required to obtain the target service fulfilling the requirements from both users and service providers. Despite many existing works have extensively handled the issue of service selection, it remains an open question in the case where requests from multiple users are performed simultaneously by a certain set of shared candidate services. Meanwhile, there exist some constraints enforced on the context of service selection, e.g. service placement location and contracts between users and service providers. In this paper, we focus on the QoS-aware service selection with constraints from a fairness aspect, with the objective of achieving max-min fairness across multiple service requests sharing candidate service sets. To be more specific, we study the problem of fairly selecting services from shared candidate sets while service providers are self-motivated to offer better services with higher QoS values. We formulate this problem as a lexicographical maximization problem, which is far from trivial to deal with practically due to its inherently multi-objective and discrete nature. A fairness-aware algorithm for concurrent service selection (FASS) is proposed, whose basic idea is to iteratively solve the single-objective subproblems by transforming them into linear programming problems. Experimental results based on real-world datasets also validate the effectiveness and practicality of our proposed approach.
Fairness-aware Generative Adversarial Network
Fairness-aware learning is increasingly important in data mining. Discrimination prevention aims to prevent discrimination in the training data before it is used to conduct predictive analysis. In this paper, we focus on fair data generation that ensures the generated data is discrimination free. Inspired by generative adversarial networks (GAN), we present fairness-aware generative adversarial networks, called FairGAN, which are able to learn a generator producing fair data and also preserving good data utility. Compared with the naive fair data generation models, FairGAN further ensures the classifiers which are trained on generated data can achieve fair classification on real data. Experiments on a real dataset show the effectiveness of FairGAN.
Fairness-Aware Re-Ranking Algorithm
Personalized recommendation brings about novel challenges in ensuring fairness, especially in scenarios in which users are not the only stakeholders involved in the recommender system. For example, the system may want to ensure that items from different providers have a fair chance of being recommended. To solve this problem, we propose a Fairness-Aware Re-ranking algorithm (FAR) to balance the ranking quality and provider-side fairness. We iteratively generate the ranking list by trading off between accuracy and the coverage of the providers. Although fair treatment of providers is desirable, users may differ in their receptivity to the addition of this type of diversity. Therefore, personalized user tolerance towards provider diversification is incorporated. Experiments are conducted on both synthetic and real-world data. The results show that our proposed re-ranking algorithm can significantly promote fairness with a slight sacrifice in accuracy and can do so while being attentive to individual user differences.
Fair-PG-Rank Conventional Learning-to-Rank (LTR) methods optimize the utility of the rankings to the users, but they are oblivious to their impact on the ranked items. However, there has been a growing understanding that the latter is important to consider for a wide range of ranking applications (e.g. online marketplaces, job placement, admissions). To address this need, we propose a general LTR framework that can optimize a wide range of utility metrics (e.g. NDCG) while satisfying fairness of exposure constraints with respect to the items. This framework expands the class of learnable ranking functions to stochastic ranking policies, which provides a language for rigorously expressing fairness specifications. Furthermore, we provide a new LTR algorithm called Fair-PG-Rank for directly searching the space of fair ranking policies via a policy-gradient approach. Beyond the theoretical evidence in deriving the framework and the algorithm, we provide empirical results on simulated and real-world datasets verifying the effectiveness of the approach in individual and group-fairness settings.
fairseq fairseq is an open-source sequence modeling toolkit that allows researchers and developers to train custom models for translation, summarization, language modeling, and other text generation tasks. The toolkit is based on PyTorch and supports distributed training across multiple GPUs and machines. We also support fast mixed-precision training and inference on modern GPUs. A demo video can be found at https://…/watch?v=OtgDdWtHvto
FairVis The growing capability and accessibility of machine learning has led to its application to many real-world domains and data about people. Despite the benefits algorithmic systems may bring, models can reflect, inject, or exacerbate implicit and explicit societal biases into their outputs, disadvantaging certain demographic subgroups. Discovering which biases a machine learning model has introduced is a great challenge, due to the numerous definitions of fairness and the large number of potentially impacted subgroups. We present FairVis, a mixed-initiative visual analytics system that integrates a novel subgroup discovery technique for users to audit the fairness of machine learning models. Through FairVis, users can apply domain knowledge to generate and investigate known subgroups, and explore suggested and similar subgroups. FairVis’ coordinated views enable users to explore a high-level overview of subgroup performance and subsequently drill down into detailed investigation of specific subgroups. We show how FairVis helps to discover biases in two real datasets used in predicting income and recidivism. As a visual analytics system devoted to discovering bias in machine learning, FairVis demonstrates how interactive visualization may help data scientists and the general public in understanding and creating more equitable algorithmic systems.
Faithfulness Condition The faithfulness condition states that also all independences among of the two possible explanations for spurious causalities of type I, we accept only the second with an additional latent confounding variable. Consequently, detection of spurious causalities of type I allows identifying spurious causalities of type II without knowing the confounding variable. the variables are implied by the causal structure. In particular, this rules out that two or more causal links cancel each other out due to a particular choice of the parameters. This means that,
FALKON Kernel methods provide a principled way to perform non linear, nonparametric learning. They rely on solid functional analytic foundations and enjoy optimal statistical properties. However, at least in their basic form, they have limited applicability in large scale scenarios because of stringent computational requirements in terms of time and especially memory. In this paper, we take a substantial step in scaling up kernel methods, proposing FALKON, a novel algorithm that allows to efficiently process millions of points. FALKON is derived combining several algorithmic principles, namely stochastic projections, iterative solvers and preconditioning. Our theoretical analysis shows that optimal statistical accuracy is achieved requiring essentially $O(n)$ memory and $O(n\sqrt{n})$ time. Extensive experiments show that state of the art results on available large scale datasets can be achieved even on a single machine.
False Confidence Theorem
Satellite conjunction analysis is the assessment of collision risk during a close encounter between a satellite and another object in orbit. A counterintuitive phenomenon has emerged in the conjunction analysis literature: probability dilution, in which lower quality data paradoxically appear to reduce the risk of collision. We show that probability dilution is a special case of a broader structural deficiency in epistemic probability distributions. In probabilistic representations of statistical inference, there are always false propositions that have a high probability of being assigned a high degree of belief. This is the false confidence theorem. As a practical matter, its manifestation in satellite conjunction analysis is particularly detrimental. Under ordinary operating conditions, satellite navigators using epistemic probability of collision as their decision-motivating risk metric are rendered incapable of detecting an impending collision. An explicit remedy for false confidence can be found in the Martin–Liu theory of inferential models. In satellite conjunction analysis, we show that Ks uncertainty ellipsoids satisfy the Martin–Liu validity criterion. Performing collision avoidance maneuvers based on ellipsoid overlap will ensure that operational collision risk is capped at the user-specified level.
An exposition of the false confidence theorem
False Discovery Rate
False discovery rate (FDR) control is a statistical method used in multiple hypothesis testing to correct for multiple comparisons. In a list of findings (i.e. studies where the null-hypotheses are rejected), FDR procedures are designed to control the expected proportion of incorrectly rejected null hypotheses (“false discoveries”). FDR controlling procedures exert a less stringent control over false discovery compared to familywise error rate (FWER) procedures (such as the Bonferroni correction), which seek to reduce the probability of even one false discovery, as opposed to the expected proportion of false discoveries. Thus FDR procedures have greater power at the cost of increased rates of type I errors, i.e., rejecting the null hypothesis of no effect when it should fail to be rejected.
False Nearest Neighbor
The false nearest neighbor algorithm is an algorithm for estimating the embedding dimension. The concept was proposed by Kennel et al. The main idea is to examine how the number of neighbors of a point along a signal trajectory change with increasing embedding dimension. In too low an embedding dimension, many of the neighbors will be false, but in an appropriate embedding dimension or higher, the neighbors are real. With increasing dimension, the false neighbors will no longer be neighbors. Therefore, by examining how the number of neighbors change as a function of dimension, an appropriate embedding can be determined.
False Positive Control Lasso In high dimensional settings where a small number of regressors are expected to be important, the Lasso estimator can be used to obtain a sparse solution vector with the expectation that most of the non-zero coefficients are associated with true signals. While several approaches have been developed to control the inclusion of false predictors with the Lasso, these approaches are limited by relying on asymptotic theory, having to empirically estimate terms based on theoretical quantities, assuming a continuous response class with Gaussian noise and design matrices, or high computation costs. In this paper we show how: (1) an existing model (the SQRT-Lasso) can be recast as a method of controlling the number of expected false positives, (2) how a similar estimator can used for all other generalized linear model classes, and (3) this approach can be fit with existing fast Lasso optimization solvers. Our justification for false positive control using randomly weighted self-normalized sum theory is to our knowledge novel. Moreover, our estimator’s properties hold in finite samples up to some approximation error which we find in practical settings to be negligible under a strict mutual incoherence condition.
False Positive Rate In statistics, when performing multiple comparisons, the term false positive ratio, also known as the false alarm ratio, usually refers to the probability of falsely rejecting the null hypothesis for a particular test. The false positive rate (or “false alarm rate”) usually refers to the expectancy of the false positive ratio.
Fama French In asset pricing and portfolio management the Fama-French three-factor model is a model designed by Eugene Fama and Kenneth French to describe stock returns.
Introduction to Fama French
Familia In the last decade, a variety of topic models have been proposed for text engineering. However, except Probabilistic Latent Semantic Analysis (PLSA) and Latent Dirichlet Allocation (LDA), most of existing topic models are seldom applied or considered in industrial scenarios. This phenomenon is caused by the fact that there are very few convenient tools to support these topic models so far. Intimidated by the demanding expertise and labor of designing and implementing parameter inference algorithms, software engineers are prone to simply resort to PLSA/LDA, without considering whether it is proper for their problem at hand or not. In this paper, we propose a configurable topic modeling framework named Familia, in order to bridge the huge gap between academic research fruits and current industrial practice. Familia supports an important line of topic models that are widely applicable in text engineering scenarios. In order to relieve burdens of software engineers without knowledge of Bayesian networks, Familia is able to conduct automatic parameter inference for a variety of topic models. Simply through changing the data organization of Familia, software engineers are able to easily explore a broad spectrum of existing topic models or even design their own topic models, and find the one that best suits the problem at hand. With its superior extendability, Familia has a novel sampling mechanism that strikes balance between effectiveness and efficiency of parameter inference. Furthermore, Familia is essentially a big topic modeling framework that supports parallel parameter inference and distributed parameter storage. The utilities and necessity of Familia are demonstrated in real-life industrial applications. Familia would significantly enlarge software engineers’ arsenal of topic models and pave the way for utilizing highly customized topic models in real-life problems.
Familywise Error Rate
In statistics, familywise error rate (FWER) is the probability of making one or more false discoveries, or type I errors, among all the hypotheses when performing multiple hypotheses tests.
Coarse-to-fine Multiple Testing Strategies
Fan Chart In time series analysis, a fan chart is a chart that joins a simple line chart for observed past data, by showing ranges for possible values of future data together with a line showing a central estimate or most likely value for the future outcomes. As predictions become increasingly uncertain the further into the future one goes, these forecast ranges spread out, creating distinctive wedge or ‘fan’ shapes, hence the term. Alternative forms of the chart can also include uncertainty for past data, such as preliminary data that is subject to revision. The term ‘fan chart’ was coined by the Bank of England, which has been using these charts and this term since 1997 in its ‘Inflation Report’ to describe its best prevision of future inflation to the general public. Fan charts have been used extensively in finance and monetary policy, for instance to represent forecasts of inflation.
FANDA Recent work on Natural Language Interfaces to Databases (NLIDB) has attracted considerable attention. NLIDB allow users to search databases using natural language instead of SQL-like query languages. While saving the users from having to learn query languages, multi-turn interaction with NLIDB usually involves multiple queries where contextual information is vital to understand the users’ query intents. In this paper, we address a typical contextual understanding problem, termed as follow-up query analysis. In spite of its ubiquity, follow-up query analysis has not been well studied due to two primary obstacles: the multifarious nature of follow-up query scenarios and the lack of high-quality datasets. Our work summarizes typical follow-up query scenarios and provides a new FollowUp dataset with $1000$ query triples on 120 tables. Moreover, we propose a novel approach FANDA, which takes into account the structures of queries and employs a ranking model with weakly supervised max-margin learning. The experimental results on FollowUp demonstrate the superiority of FANDA over multiple baselines across multiple metrics.
FanStore Emerging Deep Learning (DL) applications introduce heavy I/O workloads on computer clusters. The inherent long lasting, repeated, and random file access pattern can easily saturate the metadata and data service and negatively impact other users. In this paper, we present FanStore, a transient runtime file system that optimizes DL I/O on existing hardware/software stacks. FanStore distributes datasets to the local storage of compute nodes, and maintains a global namespace. With the techniques of system call interception, distributed metadata management, and generic data compression, FanStore provides a POSIX-compliant interface with native hardware throughput in an efficient and scalable manner. Users do not have to make intrusive code changes to use FanStore and take advantage of the optimized I/O. Our experiments with benchmarks and real applications show that FanStore can scale DL training to 512 compute nodes with over 90\% scaling efficiency.
Farewells Linear Increments Model
FLIM fits linear models for the observed increments in a longitudinal dataset, and imputes missing values according to the models.
Fast Adaptive Bilateral Filtering In the classical bilateral filter, a fixed Gaussian range kernel is used along with a spatial kernel for edge-preserving smoothing. We consider a generalization of this filter, the so-called adaptive bilateral filter, where the center and width of the Gaussian range kernel is allowed to change from pixel to pixel. Though this variant was originally proposed for sharpening and noise removal, it can also be used for other applications such as artifact removal and texture filtering. Similar to the bilateral filter, the brute-force implementation of its adaptive counterpart requires intense computations. While several fast algorithms have been proposed in the literature for bilateral filtering, most of them work only with a fixed range kernel. In this paper, we propose a fast algorithm for adaptive bilateral filtering, whose complexity does not scale with the spatial filter width. This is based on the observation that the concerned filtering can be performed purely in range space using an appropriately defined local histogram. We show that by replacing the histogram with a polynomial and the finite range-space sum with an integral, we can approximate the filter using analytic functions. In particular, an efficient algorithm is derived using the following innovations: the polynomial is fitted by matching its moments to those of the target histogram (this is done using fast convolutions), and the analytic functions are recursively computed using integration-by-parts. Our algorithm can accelerate the brute-force implementation by at least $20 \times$, without perceptible distortions in the visual quality. We demonstrate the effectiveness of our algorithm for sharpening, JPEG deblocking, and texture filtering.
Fast Alternating Minimization
Fast and Accurate Timing Error Prediction Framework
Deep neural networks (DNN) are increasingly being accelerated on application-specific hardware such as the Google TPU designed especially for deep learning. Timing speculation is a promising approach to further increase the energy efficiency of DNN accelerators. Architectural exploration for timing speculation requires detailed gate-level timing simulations that can be time-consuming for large DNNs that execute millions of multiply-and-accumulate (MAC) operations. In this paper we propose FATE, a new methodology for fast and accurate timing simulations of DNN accelerators like the Google TPU. FATE proposes two novel ideas: (i) DelayNet, a DNN based timing model for MAC units; and (ii) a statistical sampling methodology that reduces the number of MAC operations for which timing simulations are performed. We show that FATE results in between 8 times-58 times speed-up in timing simulations, while introducing less than 2% error in classification accuracy estimates. We demonstrate the use of FATE by comparing to conventional DNN accelerator that uses 2’s complement (2C) arithmetic with an alternative implementation that uses signed magnitude representations (SMR). We show that that the SMR implementation provides 18% more energy savings for the same classification accuracy than 2C, a result that might be of independent interest.
Fast and Asymptotically efficient Distributed Estimator
Consider a set of agents that wish to estimate a vector of parameters of their mutual interest. For this estimation goal, agents can sense and communicate. When sensing, an agent measures (in additive gaussian noise) linear combinations of the unknown vector of parameters. When communicating, an agent can broadcast information to a few other agents, by using the channels that happen to be randomly at its disposal at the time. To coordinate the agents towards their estimation goal, we propose a novel algorithm called FADE (Fast and Asymptotically efficient Distributed Estimator), in which agents collaborate at discrete time-steps; at each time-step, agents sense and communicate just once, while also updating their own estimate of the unknown vector of parameters. FADE enjoys five attractive features: first, it is an intuitive estimator, simple to derive; second, it withstands dynamic networks, that is, networks whose communication channels change randomly over time; third, it is strongly consistent in that, as time-steps play out, each agent’s local estimate converges (almost surely) to the true vector of parameters; fourth, it is both asymptotically unbiased and efficient, which means that, across time, each agent’s estimate becomes unbiased and the mean-square error (MSE) of each agent’s estimate vanishes to zero at the same rate of the MSE of the optimal estimator at an almighty central node; fifth, and most importantly, when compared with a state-of-art consensus+innovation (CI) algorithm, it yields estimates with outstandingly lower mean-square errors, for the same number of communications — for example, in a sparsely connected network model with 50 agents, we find through numerical simulations that the reduction can be dramatic, reaching several orders of magnitude.
Fast and Frugal Trees
Fast and Frugal Trees (FFTs) are very simply decision trees for classifying cases (i.e.; breast cancer patients) into one of two classes (e.g.; no cancer vs. true cancer). FFTs can be preferable to more complex algorithms (such as logistic regression) because they are easy to communicate and implement, and are robust against noisy data.
Fast and Robust Twin Support Vector Machine
Twin support vector machine~(TSVM) is a powerful learning algorithm by solving a pair of smaller SVM-type problems. However, there are still some specific issues waiting to be solved when it faces with some real applications, \emph{e.g}, low efficiency and noise data. In this paper, we propose a Fast and Robust TSVM~(FR-TSVM) to deal with these issues above. In FR-TSVM, we propose an effective fuzzy membership function to ease the effects of noisy inputs. We apply the fuzzy membership to each input instance and reformulate the TSVMs such that different input instances can make different contributions to the learning of the separating hyperplanes. To further speed up the training procedure, we develop an efficient coordinate descent algorithm with shirking to solve the involved a pair of quadratic programming problems (QPPs) of FR-TSVM. Moreover, theoretical foundations of the proposed model are analyzed in details. The experimental results on several artificial and benchmark datasets indicate that the FR-TSVM not only obtains the fast learning speed but also shows the robust classification performance.
“Twin Support Vector Machine”
Fast AutoAugment Data augmentation is an indispensable technique to improve generalization and also to deal with imbalanced datasets. Recently, AutoAugment has been proposed to automatically search augmentation policies from a dataset and has significantly improved performances on many image recognition tasks. However, its search method requires thousands of GPU hours to train even in a reduced setting. In this paper, we propose Fast AutoAugment algorithm that learns augmentation policies using a more efficient search strategy based on density matching. In comparison to AutoAugment, the proposed algorithm speeds up the search time by orders of magnitude while maintaining the comparable performances on the image recognition tasks with various models and datasets including CIFAR-10, CIFAR-100, and ImageNet.
Fast Boosted Decision Trees
Stochastic gradient-boosted decision trees are widely employed for multivariate classification and regression tasks. This paper presents a speed-optimized and cache-friendly implementation for multivariate classification called FastBDT. FastBDT is one order of magnitude faster during the fitting-phase and application-phase, in comparison with popular implementations in software frameworks like TMVA, scikit-learn and XGBoost. The concepts used to optimize the execution time and performance studies are discussed in detail in this paper. The key ideas include: An equal-frequency binning on the input data, which allows replacing expensive floating-point with integer operations, while at the same time increasing the quality of the classification; a cache-friendly linear access pattern to the input data, in contrast to usual implementations, which exhibit a random access pattern. FastBDT provides interfaces to C/C++, Python and TMVA. It is extensively used in the field of high energy physics by the Belle II experiment.
Fast Causal Inference
Causally insufficient structures (models with latent or hidden variables, or with confounding etc.) of joint probability distributions have been subject of intense study not only in statistics, but also in various AI systems. In AI, belief networks, being representations of joint probability distribution with an underlying directed acyclic graph structure, are paid special attention due to the fact that efficient reasoning (uncertainty propagation) methods have been developed for belief network structures. Algorithms have been therefore developed to acquire the belief network structure from data. As artifacts due to variable hiding negatively influence the performance of derived belief networks, models with latent variables have been studied and several algorithms for learning belief network structure under causal insufficiency have also been developed. Regrettably, some of them are known already to be erroneous (e.g. IC algorithm of [Pearl:Verma:91]. This paper is devoted to another algorithm, the Fast Causal Inference (FCI) Algorithm of [Spirtes:93]. It is proven by a specially constructed example that this algorithm, as it stands in [Spirtes:93], is also erroneous. Fundamental reason for failure of this algorithm is the temporary introduction of non-real links between nodes of the network with the intention of later removal. While for trivial dependency structures these non-real links may be actually removed, this may not be the case for complex ones, e.g. for the case described in this paper. A remedy of this failure is proposed.
Fast Compressed Neural Networks
FCNN (Fast Compressed Neural Networks) is a free open source C++ library for Artificial Neural Network computations. It is easy to use and extend, written in modern C++ and is very fast (to author’s best knowledge it is the fastest freely available neural network library). All FCNN classes are templated to support both single and double precision computations. Main features are listed under Features tab. Internal representation of network in FCNN differs from all other libraries allowing true code modularisation with simultaneous speed improvements.
Fast Context Adaptation via Meta-Learning
We propose CAML, a meta-learning method for fast adaptation that partitions the model parameters into two parts: context parameters that serve as additional input to the model and are adapted on individual tasks, and shared parameters that are meta-trained and shared across tasks. At test time, the context parameters are updated with one or several gradient steps on a task-specific loss that is backpropagated through the shared part of the network. Compared to approaches that adjust all parameters on a new task (e.g., MAML), our method can be scaled up to larger networks without overfitting on a single task, is easier to implement, and saves memory writes during training and network communication at test time for distributed machine learning systems. We show empirically that this approach outperforms MAML, is less sensitive to the task-specific learning rate, can capture meaningful task embeddings with the context parameters, and outperforms alternative partitionings of the parameter vectors.
Fast Data Fast Data is ‘data in motion’, data in the process of being collected or moved between applications as part of a transaction or business process flow. Fast Data is real-time data not yet stored as big data. It offers an opportunity for immediate response based on insights derived from deep analytics of incoming data streams. Fast Data processing sits in front of the big data fire hose, sifting through the massive amounts of incoming information to identify actionable business opportunities or threats.
Fast Deep Evolutionary Network Structured Evolution
This paper proposes a new extension to Deep Evolutionary Network Structured Evolution (DENSER), called Fast-DENSER++ (F-DENSER++). The vast majority of NeuroEvolution methods that optimise Deep Artificial Neural Networks (DANNs) only evaluate the candidate solutions for a fixed amount of epochs; this makes it difficult to effectively assess the learning strategy, and requires the best generated network to be further trained after evolution. F-DENSER++ enables the training time of the candidate solutions to grow continuously as necessary, i.e., in the initial generations the candidate solutions are trained for shorter times, and as generations proceed it is expected that longer training cycles enable better performances. Consequently, the models discovered by F-DENSER++ are fully-trained DANNs, and are ready for deployment after evolution, without the need for further training. The results demonstrate the ability of F-DENSER++ to effectively generate fully-trained DANNs; by the end of evolution, whilst the average performance of the models generated by F-DENSER++ is of 88.73%, the performance of the models generated by the previous version of DENSER (Fast-DENSER) is 86.91% (statistically significant), which increases to 87.76% when allowed to train for longer.
Fast Iterative Shrinkage-Thresholding Algorithm
The ‘fast iterative shrinkage-thresholding algorithm’, a.k.a. FISTA, is one of the most well-known first-order optimisation scheme in the literature, as it achieves the worst-case $O(1/k^2)$ optimal convergence rate in terms of objective function value. However, despite the optimal theoretical rate, in practice the (local) oscillatory behaviour of FISTA often damps its efficiency. Over the past years, various efforts are made in the literature to improve the practical performance of FISTA, such as monotone FISTA, restarting FISTA and backtracking strategies. In this paper, we propose a simple yet effective modification to FISTA which has two advantages: it allows us to 1) prove the convergence of generated sequence; 2) design a so-called ‘lazy-start’ strategy which can up to an order faster than the original scheme in practice. Moreover, we also propose novel adaptive and greedy strategies which can further improve the performance and outperform the state-of-the-art schemes in the literature. The advantages of the proposed schemes are illustrated through problems arising from inverse problem, machine learning and signal/image processing.
Fast Library for Approximate Nearest Neighbors
FLANN is a library for performing fast approximate nearest neighbor searches in high dimensional spaces. It contains a collection of algorithms we found to work best for nearest neighbor search and a system for automatically choosing the best algorithm and optimum parameters depending on the dataset. FLANN is written in C++ and contains bindings for the following languages: C, MATLAB and Python.
Fast Linear Iterative Clustering
Benefiting from its high efficiency and simplicity, Simple Linear Iterative Clustering (SLIC) remains one of the most popular over-segmentation tools. However, due to explicit enforcement of spatial similarity for region continuity, the boundary adaptation of SLIC is sub-optimal. It also has drawbacks on convergence rate as a result of both the fixed search region and separately doing the assignment step and the update step. In this paper, we propose an alternative approach to fix the inherent limitations of SLIC. In our approach, each pixel actively searches its corresponding segment under the help of its neighboring pixels, which naturally enables region coherence without being harmful to boundary adaptation. We also jointly perform the assignment and update steps, allowing high convergence rate. Extensive evaluations on Berkeley segmentation benchmark verify that our method outperforms competitive methods under various evaluation metrics. It also has the lowest time cost among existing methods (approximately 30fps for a 481×321 image on a single CPU core).
Fast Multipole Network
Two fundamental prerequisites for robotic multiagent systems are mobility and communication. We propose \emph{fast multipole networks} (FMNs) to achieve both ends within a unified framework. FMNs can be organized very efficiently in a distributed way from local information and are ideally suited for motion planning using artificial potentials. We compare FMNs to conventional communication topologies, and find that FMNs offer favorable communication performance in addition to their intrinsic advantages for mobility.
Fast Newton Method for Sparse Logistic Regression
Sparse logistic regression has been developed tremendously in recent two decades, from its origination the $\ell_1$-regularized version by Tibshirani(1996) to the sparsity constrained models by Bahmani, Raj, and Boufounos (2013); Plan and Vershynin (2013). This paper is carried out on the sparsity constrained logistic regression through the classical Newton method. We begin with analysing its first optimality condition to acquire a strong $\tau$-stationary point for some $\tau>0$. This point enables us to equivalently derive a stationary equation system which is able to be efficiently solved by Newton method. The proposed method FNSLR, an abbreviation for Newton method for sparse logistic regression, enjoys a very low computational complexity, local quadratic convergence rate and termination within finite steps. Numerical experiments on random data and real data demonstrate its superior performance when against with seven state-of-the-art solvers.
Fast Oriented Text Spotting
Incidental scene text spotting is considered one of the most difficult and valuable challenges in the document analysis community. Most existing methods treat text detection and recognition as separate tasks. In this work, we propose a unified end-to-end trainable Fast Oriented Text Spotting (FOTS) network for simultaneous detection and recognition, sharing computation and visual information among the two complementary tasks. Specially, RoIRotate is introduced to share convolutional features between detection and recognition. Benefiting from convolution sharing strategy, our FOTS has little computation overhead compared to baseline text detection network, and the joint training method learns more generic features to make our method perform better than these two-stage methods. Experiments on ICDAR 2015, ICDAR 2017 MLT, and ICDAR 2013 datasets demonstrate that the proposed method outperforms state-of-the-art methods significantly, which further allows us to develop the first real-time oriented text spotting system which surpasses all previous state-of-the-art results by more than 5% on ICDAR 2015 text spotting task while keeping 22.6 fps.
Fast Parallel Proximal Algorithm
Learning-based Image Reconstruction via Parallel Proximal Algorithm
Fast Randomized PCA Principal component analysis (PCA) is widely used for dimension reduction and embedding of real data in social network analysis, information retrieval, and natural language processing, etc. In this work we propose a fast randomized PCA algorithm for processing large sparse data. The algorithm has similar accuracy to the basic randomized SVD (rPCA) algorithm (Halko et al., 2011), but is largely optimized for sparse data. It also has good flexibility to trade off runtime against accuracy for practical usage. Experiments on real data show that the proposed algorithm is up to 9.1X faster than the basic rPCA algorithm without accuracy loss, and is up to 20X faster than the svds in Matlab with little error. The algorithm computes the first 100 principal components of a large information retrieval data with 12,869,521 persons and 323,899 keywords in less than 400 seconds on a 24-core machine, while all conventional methods fail due to the out-of-memory issue.
Fast Rotation Forest Ensemble approaches in classification are a very popular research area in recent years. An ensemble consists of a set of individual classifiers such as neural networks or decision trees whose predictions are combined for classifying new instances. A method is used here for generating classifier ensembles based on feature extraction. In the base classifier, the feature set is randomly split into K subsets (K is a parameter of the algorithm) and Principal Component Analysis (PCA) is applied to each subset. It is a technique that is useful for the extraction and classification of data. The purpose is to reduce the dimensionality of a data set. Then the Decision tree is used to classify the data set. Rotation Forest and Extended Space Forest algorithms are used to calculate the accuracy. A novel approach Fast Rotation Forest is introduced to enrich the accuracy rate. The idea of the fast rotation approach is to encourage simultaneously individual accuracy and specificity within the ensemble. By comparing Random forest and Extended Space Forest, Fast Rotation Forest yields high accuracy.
Fast Segmentation Convolutional Neural Network
The encoder-decoder framework is state-of-the-art for offline semantic image segmentation. Since the rise in autonomous systems, real-time computation is increasingly desirable. In this paper, we introduce fast segmentation convolutional neural network (Fast-SCNN), an above real-time semantic segmentation model on high resolution image data (1024x2048px) suited to efficient computation on embedded devices with low memory. Building on existing two-branch methods for fast segmentation, we introduce our `learning to downsample’ module which computes low-level features for multiple resolution branches simultaneously. Our network combines spatial detail at high resolution with deep features extracted at lower resolution, yielding an accuracy of 68.0% mean intersection over union at 123.5 frames per second on Cityscapes. We also show that large scale pre-training is unnecessary. We thoroughly validate our metric in experiments with ImageNet pre-training and the coarse labeled data of Cityscapes. Finally, we show even faster computation with competitive results on subsampled inputs, without any network modifications.
Fast Shannon Mutual Information
Exploration tasks are embedded in many robotics applications, such as search and rescue and space exploration. Information-based exploration algorithms aim to find the most informative trajectories by maximizing an information-theoretic metric, such as the mutual information between the map and potential future measurements. Unfortunately, most existing information-based exploration algorithms are plagued by the computational difficulty of evaluating the Shannon mutual information metric. In this paper, we consider the fundamental problem of evaluating Shannon mutual information between the map and a range measurement. First, we consider 2D environments. We propose a novel algorithm, called the Fast Shannon Mutual Information (FSMI). The key insight behind the algorithm is that a certain integral can be computed analytically, leading to substantial computational savings. Second, we consider 3D environments, represented by efficient data structures, e.g., an OctoMap, such that the measurements are compressed by Run-Length Encoding (RLE). We propose a novel algorithm, called FSMI-RLE (Fast Shannon Mutual Information Run-Length Encoding), that efficiently evaluates the Shannon mutual information when the measurements are compressed using RLE. For both the FSMI and the FSMI-RLE, we also propose variants that make different assumptions on the sensor noise distribution for the purpose of further computational savings. We evaluate the proposed algorithms in extensive experiments. In particular, we show that the proposed algorithms outperform existing algorithms that compute Shannon mutual information as well as other algorithms that compute the Cauchy-Schwarz Quadratic mutual information (CSQMI). In addition, we demonstrate the computation of Shannon mutual information on a 3D map for the first time.
Fast Shannon Mutual Information Run-Length Encoding
Exploration tasks are embedded in many robotics applications, such as search and rescue and space exploration. Information-based exploration algorithms aim to find the most informative trajectories by maximizing an information-theoretic metric, such as the mutual information between the map and potential future measurements. Unfortunately, most existing information-based exploration algorithms are plagued by the computational difficulty of evaluating the Shannon mutual information metric. In this paper, we consider the fundamental problem of evaluating Shannon mutual information between the map and a range measurement. First, we consider 2D environments. We propose a novel algorithm, called the Fast Shannon Mutual Information (FSMI). The key insight behind the algorithm is that a certain integral can be computed analytically, leading to substantial computational savings. Second, we consider 3D environments, represented by efficient data structures, e.g., an OctoMap, such that the measurements are compressed by Run-Length Encoding (RLE). We propose a novel algorithm, called FSMI-RLE, that efficiently evaluates the Shannon mutual information when the measurements are compressed using RLE. For both the FSMI and the FSMI-RLE, we also propose variants that make different assumptions on the sensor noise distribution for the purpose of further computational savings. We evaluate the proposed algorithms in extensive experiments. In particular, we show that the proposed algorithms outperform existing algorithms that compute Shannon mutual information as well as other algorithms that compute the Cauchy-Schwarz Quadratic mutual information (CSQMI). In addition, we demonstrate the computation of Shannon mutual information on a 3D map for the first time.
Fast Similarity Search
Fast Similarity Search (FastSS) performs an exhaustive similarity search in a dictionary, based on the edit distance model of string similarity. The algorithm uses deletions to model the edit distance. For a dictionary containing n words, and given a maximum number of spelling errors k, FastSS creates an index of all n words containing up to k deletions. At search time each query is mutated to generate a deletion neighborhood, which is compared to the indexed deletion dictionary.
Fast Supervised Discrete Hashing
Learning-based hashing algorithms are “hot topics’ because they can greatly increase the scale at which existing methods operate. In this paper, we propose a new learning-based hashing method called “fast supervised discrete hashing’ (FSDH) based on “supervised discrete hashing’ (SDH). Regressing the training examples (or hash code) to the corresponding class labels is widely used in ordinary least squares regression. Rather than adopting this method, FSDH uses a very simple yet effective regression of the class labels of training examples to the corresponding hash code to accelerate the algorithm. To the best of our knowledge, this strategy has not previously been used for hashing. Traditional SDH decomposes the optimization into three sub-problems, with the most critical sub-problem – discrete optimization for binary hash codes – solved using iterative discrete cyclic coordinate descent (DCC), which is time-consuming. However, FSDH has a closed-form solution and only requires a single rather than iterative hash code-solving step, which is highly efficient. Furthermore, FSDH is usually faster than SDH for solving the projection matrix for least squares regression, making FSDH generally faster than SDH. For example, our results show that FSDH is about 12-times faster than SDH when the number of hashing bits is 128 on the CIFAR-10 data base, and FSDH is about 151-times faster than FastHash when the number of hashing bits is 64 on the MNIST data-base. Our experimental results show that FSDH is not only fast, but also outperforms other comparative methods.
Fast Task-Aware Architecture Inference Neural architecture search has been shown to hold great promise towards the automation of deep learning. However in spite of its potential, neural architecture search remains quite costly. To this point, we propose a novel gradient-based framework for efficient architecture search by sharing information across several tasks. We start by training many model architectures on several related (training) tasks. When a new unseen task is presented, the framework performs architecture inference in order to quickly identify a good candidate architecture, before any model is trained on the new task. At the core of our framework lies a deep value network that can predict the performance of input architectures on a task by utilizing task meta-features and the previous model training experiments performed on related tasks. We adopt a continuous parametrization of the model architecture which allows for efficient gradient-based optimization. Given a new task, an effective architecture is quickly identified by maximizing the estimated performance with respect to the model architecture parameters with simple gradient ascent. It is key to point out that our goal is to achieve reasonable performance at the lowest cost. We provide experimental results showing the effectiveness of the framework despite its high computational efficiency.
Fast Temporal Pattern Mining with Extended Vertical Lists Temporal Pattern Mining (TPM) is the problem of mining predictive complex temporal patterns from multivariate time series in a supervised setting. We develop a new method called the Fast Temporal Pattern Mining with Extended Vertical Lists. This method utilizes an extension of the Apriori property which requires a more complex pattern to appear within records only at places where all of its subpatterns are detected as well. The approach is based on a novel data structure called the Extended Vertical List that tracks positions of the first state of the pattern inside records. Extensive computational results indicate that the new method performs significantly faster than the previous version of the algorithm for TMP. However, the speed-up comes at the expense of memory usage.
Fast Weight Long Short-Term Memory Associative memory using fast weights is a short-term memory mechanism that substantially improves the memory capacity and time scale of recurrent neural networks (RNNs). As recent studies introduced fast weights only to regular RNNs, it is unknown whether fast weight memory is beneficial to gated RNNs. In this work, we report a significant synergy between long short-term memory (LSTM) networks and fast weight associative memories. We show that this combination, in learning associative retrieval tasks, results in much faster training and lower test error, a performance boost most prominent at high memory task difficulties.
FastContext Objective: To develop and evaluate FastContext, an efficient, scalable implementation of the ConText algorithm suitable for very large-scale clinical natural language processing. Background: The ConText algorithm performs with state-of-art accuracy in detecting the experiencer, negation status, and temporality of concept mentions in clinical narratives. However, the speed limitation of its current implementations hinders its use in big data processing. Methods: We developed FastContext through hashing the ConText’s rules, then compared its speed and accuracy with JavaConText and GeneralConText, two widely used Java implementations. Results: FastContext ran two orders of magnitude faster and was less decelerated by rule increase than the other two implementations used in this study for comparison. Additionally, FastContext consistently gained accuracy improvement as the rules increased (the desired outcome of adding new rules), while the other two implementations did not. Conclusions: FastContext is an efficient, scalable implementation of the popular ConText algorithm, suitable for natural language applications on very large clinical corpora.
FastDeepIoT Deep neural networks show great potential as solutions to many sensing application problems, but their excessive resource demand slows down execution time, pausing a serious impediment to deployment on low-end devices. To address this challenge, recent literature focused on compressing neural network size to improve performance. We show that changing neural network size does not proportionally affect performance attributes of interest, such as execution time. Rather, extreme run-time nonlinearities exist over the network configuration space. Hence, we propose a novel framework, called FastDeepIoT, that uncovers the non-linear relation between neural network structure and execution time, then exploits that understanding to find network configurations that significantly improve the trade-off between execution time and accuracy on mobile and embedded devices. FastDeepIoT makes two key contributions. First, FastDeepIoT automatically learns an accurate and highly interpretable execution time model for deep neural networks on the target device. This is done without prior knowledge of either the hardware specifications or the detailed implementation of the used deep learning library. Second, FastDeepIoT informs a compression algorithm how to minimize execution time on the profiled device without impacting accuracy. We evaluate FastDeepIoT using three different sensing-related tasks on two mobile devices: Nexus 5 and Galaxy Nexus. FastDeepIoT further reduces the neural network execution time by $48\%$ to $78\%$ and energy consumption by $37\%$ to $69\%$ compared with the state-of-the-art compression algorithms.
FastFCN Modern approaches for semantic segmentation usually employ dilated convolutions in the backbone to extract high-resolution feature maps, which brings heavy computation complexity and memory footprint. To replace the time and memory consuming dilated convolutions, we propose a novel joint upsampling module named Joint Pyramid Upsampling (JPU) by formulating the task of extracting high-resolution feature maps into a joint upsampling problem. With the proposed JPU, our method reduces the computation complexity by more than three times without performance loss. Experiments show that JPU is superior to other upsampling modules, which can be plugged into many existing approaches to reduce computation complexity and improve performance. By replacing dilated convolutions with the proposed JPU module, our method achieves the state-of-the-art performance in Pascal Context dataset (mIoU of 53.13%) and ADE20K dataset (final score of 0.5584) while running 3 times faster.
FastFusionNet In this technical report, we introduce FastFusionNet, an efficient variant of FusionNet [12]. FusionNet is a high performing reading comprehension architecture, which was designed primarily for maximum retrieval accuracy with less regard towards computational requirements. For FastFusionNets we remove the expensive CoVe layers [21] and substitute the BiLSTMs with far more efficient SRU layers [19]. The resulting architecture obtains state-of-the-art results on DAWNBench [5] while achieving the lowest training and inference time on SQuAD [25] to-date. The code is available at https://…/FastFusionNet.
FastICA FastICA is an efficient and popular algorithm for independent component analysis invented by Aapo Hyvaerinen at Helsinki University of Technology. The algorithm is based on a fixed-point iteration scheme maximizing non-Gaussianity as a measure of statistical independence. It can also be derived as an approximative Newton iteration.
Fast-Node2Vec Node2Vec is a state-of-the-art general-purpose feature learning method for network analysis. However, current solutions cannot run Node2Vec on large-scale graphs with billions of vertices and edges, which are common in real-world applications. The existing distributed Node2Vec on Spark incurs significant space and time overhead. It runs out of memory even for mid-sized graphs with millions of vertices. Moreover, it considers at most 30 edges for every vertex in generating random walks, causing poor result quality. In this paper, we propose Fast-Node2Vec, a family of efficient Node2Vec random walk algorithms on a Pregel-like graph computation framework. Fast-Node2Vec computes transition probabilities during random walks to reduce memory space consumption and computation overhead for large-scale graphs. The Pregel-like scheme avoids space and time overhead of Spark’s read-only RDD structures and shuffle operations. Moreover, we propose a number of optimization techniques to further reduce the computation overhead for popular vertices with large degrees. Empirical evaluation show that Fast-Node2Vec is capable of computing Node2Vec on graphs with billions of vertices and edges on a mid-sized machine cluster. Compared to Spark-Node2Vec, Fast-Node2Vec achieves 7.7–122x speedups.
Fast-Slow Recurrent Neural Networks
Processing sequential data of variable length is a major challenge in a wide range of applications, such as speech recognition, language modeling, generative image modeling and machine translation. Here, we address this challenge by proposing a novel recurrent neural network (RNN) architecture, the Fast-Slow RNN (FS-RNN). The FS-RNN incorporates the strengths of both multiscale RNNs and deep transition RNNs as it processes sequential data on different timescales and learns complex transition functions from one time step to the next. We evaluate the FS-RNN on two character level language modeling data sets, Penn Treebank and Hutter Prize Wikipedia, where we improve state of the art results to $1.19$ and $1.25$ bits-per-character (BPC), respectively. In addition, an ensemble of two FS-RNNs achieves $1.20$ BPC on Hutter Prize Wikipedia outperforming the best known compression algorithm with respect to the BPC measure. We also present an empirical investigation of the learning and network dynamics of the FS-RNN, which explains the improved performance compared to other RNN architectures. Our approach is general as any kind of RNN cell is a possible building block for the FS-RNN architecture, and thus can be flexibly applied to different tasks.
Fast-Super Paramagnetic Clustering An Introduction to fast-Super Paramagnetic Clustering
fastText fastText is a library for efficient learning of word representations and sentence classification.
Analysis and Optimization of fastText Linear Text Classifier
FATSO In linear models it is common to have situations where several regression coefficients are zero. In these situations a common tool to perform regression is a variable selection operator. One of the most common such operators is the LASSO operator, which promotes point estimates which are zero. The LASSO operator and similar approaches, however, give little in terms of easily interpretable parameters to determine the degree of variable selectivity. In this paper we propose a new family of selection operators which builds on the geometry of LASSO but which yield an easily interpretable way to tune selectivity. These operators correspond to Bayesian prior densities and hence are suitable for Bayesian inference. We present some examples using simulated and real data, with promising results.
Fault Tree Analysis
Fault tree analysis (FTA) is a top down, deductive failure analysis in which an undesired state of a system is analyzed using Boolean logic to combine a series of lower-level events. This analysis method is mainly used in the fields of safety engineering and reliability engineering to understand how systems can fail, to identify the best ways to reduce risk or to determine (or get a feeling for) event rates of a safety accident or a particular system level (functional) failure. FTA is used in the aerospace, nuclear power, chemical and process, pharmaceutical, petrochemical and other high-hazard industries; but is also used in fields as diverse as risk factor identification relating to social service system failure. FTA is also used in software engineering for debugging purposes and is closely related to cause-elimination technique used to detect bugs. In aerospace, the more general term ‘system Failure Condition’ is used for the ‘undesired state’ / Top event of the fault tree. These conditions are classified by the severity of their effects. The most severe conditions require the most extensive fault tree analysis. These ‘system Failure Conditions’ and their classification are often previously determined in the functional Hazard analysis.
Fault Tree Analysis (FTA): Concepts and Applications
Fay Herriot Model smallarea
FBNet Designing accurate and efficient ConvNets for mobile devices is challenging because the design space is combinatorially large. Due to this, previous neural architecture search (NAS) methods are computationally expensive. ConvNet architecture optimality depends on factors such as input resolution and target devices. However, existing approaches are too expensive for case-by-case redesigns. Also, previous work focuses primarily on reducing FLOPs, but FLOP count does not always reflect actual latency. To address these, we propose a differentiable neural architecture search (DNAS) framework that uses gradient-based methods to optimize ConvNet architectures, avoiding enumerating and training individual architectures separately as in previous methods. FBNets, a family of models discovered by DNAS surpass state-of-the-art models both designed manually and generated automatically. FBNet-B achieves 74.1% top-1 accuracy on ImageNet with 295M FLOPs and 23.1 ms latency on a Samsung S8 phone, 2.4x smaller and 1.5x faster than MobileNetV2-1.3 with similar accuracy. Despite higher accuracy and lower latency than MnasNet, we estimate FBNet-B’s search cost is 420x smaller than MnasNet’s, at only 216 GPU-hours. Searched for different resolutions and channel sizes, FBNets achieve 1.5% to 6.4% higher accuracy than MobileNetV2. The smallest FBNet achieves 50.2% accuracy and 2.9 ms latency (345 frames per second) on a Samsung S8. Over a Samsung-optimized FBNet, the iPhone-X-optimized model achieves a 1.4x speedup on an iPhone X.
F-DENSER++ “Fast Deep Evolutionary Network Structured Evolution”
f-differential privacy Differential privacy has seen remarkable success as a rigorous and practical formalization of data privacy in the past decade. But it also has some well known weaknesses: notably, it does not tightly handle composition. This weakness has inspired several recent relaxations of differential privacy based on Renyi divergences. We propose an alternative relaxation of differential privacy, which we term ‘$f$-differential privacy’, which has a number of appealing properties and avoids some of the difficulties associated with divergence based relaxations. First, it preserves the hypothesis testing interpretation of differential privacy, which makes its guarantees easily interpretable. It allows for lossless reasoning about composition and post-processing, and notably, a direct way to import existing tools from differential privacy, including privacy amplification by subsampling. We define a canonical single parameter family of definitions within our class which we call ‘Gaussian Differential Privacy’, defined based on the hypothesis testing of two shifted Gaussian distributions. We show that this family is focal by proving a central limit theorem, which shows that the privacy guarantees of \emph{any} hypothesis-testing based definition of privacy (including differential privacy) converges to Gaussian differential privacy in the limit under composition. We also prove a finite (Berry-Esseen style) version of the central limit theorem, which gives a useful tool for tractably analyzing the exact composition of potentially complicated expressions. We demonstrate the use of the tools we develop by giving an improved analysis of the privacy guarantees of noisy stochastic gradient descent.
FearNet Incremental class learning involves sequentially learning classes in bursts of examples from the same class. This violates the assumptions that underlie methods for training standard deep neural networks, and will cause them to suffer from catastrophic forgetting. Arguably, the best method for incremental class learning is iCaRL, but it requires storing training examples for each class, making it challenging to scale. Here, we propose FearNet for incremental class learning. FearNet is a generative model that does not store previous examples, making it memory efficient. FearNet uses a brain-inspired dual-memory system in which new memories are consolidated from a network for recent memories inspired by the mammalian hippocampal complex to a network for long-term storage inspired by medial prefrontal cortex. Memory consolidation is inspired by mechanisms that occur during sleep. FearNet also uses a module inspired by the basolateral amygdala for determining which memory system to use for recall. FearNet achieves state-of-the-art performance at incremental class learning on image (CIFAR-100, CUB-200) and audio classification (AudioSet) benchmarks.
Feasible Graphical Lasso
In this paper, we investigate seemingly unrelated regression (SUR) models that allow the number of equations (N) to be large, and to be comparable to the number of the observations in each equation (T). It is well known in the literature that the conventional SUR estimator, for example, the generalized least squares (GLS) estimator of Zellner (1962) does not perform well. As the main contribution of the paper, we propose a new feasible GLS estimator called the feasible graphical lasso (FGLasso) estimator. For a feasible implementation of the GLS estimator, we use the graphical lasso estimation of the precision matrix (the inverse of the covariance matrix of the equation system errors) assuming that the underlying unknown precision matrix is sparse. We derive asymptotic theories of the new estimator and investigate its finite sample properties via Monte-Carlo simulations.
FeatherNet Face Anti-spoofing gains increased attentions recently in both academic and industrial fields. With the emergence of various CNN based solutions, the multi-modal(RGB, depth and IR) methods based CNN showed better performance than single modal classifiers. However, there is a need for improving the performance and reducing the complexity. Therefore, an extreme light network architecture(FeatherNet A/B) is proposed with a streaming module which fixes the weakness of Global Average Pooling and uses less parameters. Our single FeatherNet trained by depth image only, provides a higher baseline with 0.00168 ACER, 0.35M parameters and 83M FLOPS. Furthermore, a novel fusion procedure with “ensemble + cascade” structure is presented to satisfy the performance preferred use cases. Meanwhile, the MMFD dataset is collected to provide more attacks and diversity to gain better generalization. We use the fusion method in the Face Anti-spoofing Attack Detection Challenge@CVPR2019 and got the result of 0.0013(ACER), 0.999(TPR@FPR=10e-2), 0.998(TPR@FPR=10e-3) and 0.9814(TPR@FPR=10e-4).
Feature Bagging-based Outlier Detection
In this paper, a novel feature bagging approach for detecting outliers in very large, high dimensional and noisy databases is proposed. It combines results from multiple outlier detection algorithms that are applied using different set of features. Every outlier detection algorithm uses a small subset of features that are randomly selected from the original feature set. As a result, each outlier detector identifies different outliers, and thus assigns to all data records outlier scores that correspond to their probability of being outliers. The outlier scores computed by the individual outlier detection algorithms are then combined in order to find the better quality outliers. Experiments performed on several synthetic and real life data sets show that the proposed methods for combining outputs from multiple outlier detection algorithms provide non-trivial improvements over the base algorithm.
Feature Boosting and Suppression
Making deep convolutional neural networks more accurate typically comes at the cost of increased computational and memory resources. In this paper, we exploit the fact that the importance of features computed by convolutional layers is highly input-dependent, and propose feature boosting and suppression (FBS), a new method to predictively amplify salient convolutional channels and skip unimportant ones at run-time. FBS introduces small auxiliary connections to existing convolutional layers. In contrast to channel pruning methods which permanently remove channels, it preserves the full network structures and accelerates convolution by dynamically skipping unimportant input and output channels. FBS-augmented networks are trained with conventional stochastic gradient descent, making it readily available for many state-of-the-art CNNs. We compare FBS to a range of existing channel pruning and dynamic execution schemes and demonstrate large improvements on ImageNet classification. Experiments show that FBS can accelerate VGG-16 by $5\times$ and improve the speed of ResNet-18 by $2\times$, both with less than $0.6\%$ top-5 accuracy loss.
Feature Crossing Feature crossing captures interactions among categorical features and is useful to enhance learning from tabular data in real-world businesses.
Feature Engineering Feature engineering is the process of determining which predictor variables will contribute the most to the predictive power of a machine learning algorithm. There are two commonly used methods for making this selection – the Forward Selection Procedure starts with no variables in the model. You then iteratively add variables and test the predictive accuracy of the model until adding more variables no longer makes a positive effect. Next, the Backward Elimination Procedure begins with all the variables in the model. You proceed by removing variables and testing the predictive accuracy of the model.
Feature Engineering Wrapper
We propose a general wrapper for feature learning that interfaces with other machine learning methods to compose effective data representations. The proposed feature engineering wrapper (FEW) uses genetic programming to represent and evolve individual features tailored to the machine learning method with which it is paired. In order to maintain feature diversity,lexicase survival is introduced, a method based on lexicase selection. This survival method preserves semantically unique individuals in the population based on their ability to solve difficult subsets of training cases, thereby yielding a population of uncorrelated features. We demonstrate FEW with five different off-the-shelf machine learning methods and test it on a set of real-world and synthetic regression problems with dimensions varying across three orders of magnitude. The results show that FEW is able to improve model test predictions across problems for several ML methods. We discuss and test the scalability of FEW in comparison to other feature composition strategies, most notably polynomial feature expansion.
Feature Evolvable Streaming Learning Learning with streaming data has attracted much attention during the past few years. Though most studies consider data stream with fixed features, in real practice the features may be evolvable. For example, features of data gathered by limited-lifespan sensors will change when these sensors are substituted by new ones. In this paper, we propose a novel learning paradigm: Feature Evolvable Streaming Learning where old features would vanish and new features will occur. Rather than relying on only the current features, we attempt to recover the vanished features and exploit it to improve performance. Specifically, we learn two models from the recovered features and the current features, respectively. To benefit from the recovered features, we develop two ensemble methods. In the first method, we combine the predictions from two models and theoretically show that with assistance of old features, the performance on new features can be improved. In the second approach, we dynamically select the best single prediction and establish a better performance guarantee when the best model switches. Experiments on both synthetic and real data validate the effectiveness of our proposal.
Feature Fusion Learning
We propose a learning framework named Feature Fusion Learning (FFL) that efficiently trains a powerful classifier through a fusion module which combines the feature maps generated from parallel neural networks. Specifically, we train a number of parallel neural networks as sub-networks, then we combine the feature maps from each sub-network using a fusion module to create a more meaningful feature map. The fused feature map is passed into the fused classifier for overall classification. Unlike existing feature fusion methods, in our framework, an ensemble of sub-network classifiers transfers its knowledge to the fused classifier and then the fused classifier delivers its knowledge back to each sub-network, mutually teaching one another in an online-knowledge distillation manner. This mutually teaching system not only improves the performance of the fused classifier but also obtains performance gain in each sub-network. Moreover, our model is more beneficial because different types of network can be used for each sub-network. We have performed a variety of experiments on multiple datasets such as CIFAR-10, CIFAR-100 and ImageNet and proved that our method is more effective than other alternative methods in terms of performance of both sub-networks and the fused classifier.
Feature Fusion Single Shot Multibox Detector
SSD (Single Shot Multibox Detetor) is one of the best object detection algorithms with both high accuracy and fast speed. However, SSD’s feature pyramid detection method makes it hard to fuse the features from different scales. In this paper, we proposed FSSD (Feature Fusion Single Shot Multibox Detector), an enhanced SSD with a novel and lightweight feature fusion module which can improve the performance significantly over SSD with just a little speed drop. In the feature fusion module, features from different layers with different scales are concatenated together, followed by some down-sampling blocks to generate new feature pyramid, which will be fed to multibox detectors to predict the final detection results. On the Pascal VOC 2007 test, our network can achieve 82.7 mAP (mean average precision) at the speed of 65.8 FPS (frame per second) with the input size 300$\times$300 using a single Nvidia 1080Ti GPU. In addition, our result on COCO is also better than the conventional SSD with a large margin. Our FSSD outperforms a lot of state-of-the-art object detection algorithms in both aspects of accuracy and speed. Code will be made publicly available.
Feature Generation by Convolutional Neural Network
Click-Through Rate prediction is an important task in recommender systems, which aims to estimate the probability of a user to click on a given item. Recently, many deep models have been proposed to learn low-order and high-order feature interactions from original features. However, since useful interactions are always sparse, it is difficult for DNN to learn them effectively under a large number of parameters. In real scenarios, artificial features are able to improve the performance of deep models (such as Wide & Deep Learning), but feature engineering is expensive and requires domain knowledge, making it impractical in different scenarios. Therefore, it is necessary to augment feature space automatically. In this paper, We propose a novel Feature Generation by Convolutional Neural Network (FGCNN) model with two components: Feature Generation and Deep Classifier. Feature Generation leverages the strength of CNN to generate local patterns and recombine them to generate new features. Deep Classifier adopts the structure of IPNN to learn interactions from the augmented feature space. Experimental results on three large-scale datasets show that FGCNN significantly outperforms nine state-of-the-art models. Moreover, when applying some state-of-the-art models as Deep Classifier, better performance is always achieved, showing the great compatibility of our FGCNN model. This work explores a novel direction for CTR predictions: it is quite useful to reduce the learning difficulties of DNN by automatically identifying important features.
Feature Importance and Bilinear feature Interaction NETwork
Advertising and feed ranking are essential to many Internet companies such as Facebook and Sina Weibo. Among many real-world advertising and feed ranking systems, click through rate (CTR) prediction plays a central role. There are many proposed models in this field such as logistic regression, tree based models, factorization machine based models and deep learning based CTR models. However, many current works calculate the feature interactions in a simple way such as Hadamard product and inner product and they care less about the importance of features. In this paper, a new model named FiBiNET as an abbreviation for Feature Importance and Bilinear feature Interaction NETwork is proposed to dynamically learn the feature importance and fine-grained feature interactions. On the one hand, the FiBiNET can dynamically learn the importance of features via the Squeeze-Excitation network (SENET) mechanism; on the other hand, it is able to effectively learn the feature interactions via bilinear function. We conduct extensive experiments on two real-world datasets and show that our shallow model outperforms other shallow models such as factorization machine(FM) and field-aware factorization machine(FFM). In order to improve performance further, we combine a classical deep neural network(DNN) component with the shallow model to be a deep model. The deep FiBiNET consistently outperforms the other state-of-the-art deep models such as DeepFM and extreme deep factorization machine(XdeepFM).
Feature Learning Feature learning or representation learning is a set of techniques in machine learning that learn a transformation of “raw” inputs to a representation that can be effectively exploited in a supervised learning task such as classification. Feature learning algorithms themselves may be either unsupervised or supervised, and include autoencoders, dictionary learning, matrix factorization, restricted Boltzmann machines and various form of clustering.
Feature Matching MatchBench: An Evaluation of Feature Matchers
Feature Pyramid Hashing In recent years, deep-networks-based hashing has become a leading approach for large-scale image retrieval. Most deep hashing approaches use the high layer to extract the powerful semantic representations. However, these methods have limited ability for fine-grained image retrieval because the semantic features extracted from the high layer are difficult in capturing the subtle differences. To this end, we propose a novel two-pyramid hashing architecture to learn both the semantic information and the subtle appearance details for fine-grained image search. Inspired by the feature pyramids of convolutional neural network, a vertical pyramid is proposed to capture the high-layer features and a horizontal pyramid combines multiple low-layer features with structural information to capture the subtle differences. To fuse the low-level features, a novel combination strategy, called consensus fusion, is proposed to capture all subtle information from several low-layers for finer retrieval. Extensive evaluation on two fine-grained datasets CUB-200-2011 and Stanford Dogs demonstrate that the proposed method achieves significant performance compared with the state-of-art baselines.
Feature Pyramid Network
Panoptic Feature Pyramid Networks
Feature Refine Net
This paper presents a method that can accurately detect heads especially small heads under indoor scene. To achieve this, we propose a novel Feature Refine Net (FRN) and a cascaded multi-scale architecture. FRN exploits the multi-scale hierarchical features created by deep convolutional neural networks. Proposed channel weighting method enables FRN to make use of features alternatively and effectively. To improve the performance of small head detection, we propose a cascaded multi-scale architecture which has two detectors. One called global detector is responsible for detecting large objects and acquiring the global distribution information. The other called local detector is specified for small objects detection and makes use of the information provided by global detector. Due to the lack of head detection datasets, we have collected and labeled a new large dataset named SCUT-HEAD that includes 4405 images with 111251 heads annotated. Experiments show that our method has achieved state-of-art performance on SCUT-HEAD.
Feature Relevance Interval
Most existing feature selection methods are insufficient for analytic purposes as soon as high dimensional data or redundant sensor signals are dealt with since features can be selected due to spurious effects or correlations rather than causal effects. To support the finding of causal features in biomedical experiments, we hereby present FRI, an open source Python library that can be used to identify all-relevant variables in linear classification and (ordinal) regression problems. Using the recently proposed feature relevance method, FRI is able to provide the base for further general experimentation or in specific can facilitate the search for alternative biomarkers. It can be used in an interactive context, by providing model manipulation and visualization methods, or in a batch process as a filter method.
Feature Sampling Deep Neural Networks (DNNs) thrive in recent years in which Batch Normalization (BN) plays an indispensable role. However, it has been observed that BN is costly due to the reduction operations. In this paper, we propose alleviating this problem through sampling only a small fraction of data for normalization at each iteration. Specifically, we model it as a statistical sampling problem and identify that by sampling less correlated data, we can largely reduce the requirement of the number of data for statistics estimation in BN, which directly simplifies the reduction operations. Based on this conclusion, we propose two sampling strategies, ‘Batch Sampling’ (randomly select several samples from each batch) and ‘Feature Sampling’ (randomly select a small patch from each feature map of all samples), that take both computational efficiency and sample correlation into consideration. Furthermore, we introduce an extremely simple variant of BN, termed as Virtual Dataset Normalization (VDN), that can normalize the activations well with few synthetical random samples. All the proposed methods are evaluated on various datasets and networks, where an overall training speedup by up to 20% on GPU is practically achieved without the support of any specialized libraries, and the loss on accuracy and convergence rate are negligible. Finally, we extend our work to the ‘micro-batch normalization’ problem and yield comparable performance with existing approaches at the case of tiny batch size.
Feature Scaling Feature scaling is a method used to standardize the range of independent variables or features of data. In data processing, it is also known as data normalization and is generally performed during the data preprocessing step.
Feature Screening Feature screening is a powerful tool in the analysis of high dimensional data. When the sample size $N$ and the number of features $p$ are both large, the implementation of classic screening methods can be numerically challenging.
Feature Selection In machine learning and statistics, feature selection, also known as variable selection, attribute selection or variable subset selection, is the process of selecting a subset of relevant features for use in model construction. The central assumption when using a feature selection technique is that the data contains many redundant or irrelevant features. Redundant features are those which provide no more information than the currently selected features, and irrelevant features provide no useful information in any context. Feature selection techniques are a subset of the more general field of feature extraction.
FEAture Selection for compilation Tasks
The success of the application of machine-learning techniques to compilation tasks can be largely attributed to the recent development and advancement of program characterization, a process that numerically or structurally quantifies a target program. While great achievements have been made in identifying key features to characterize programs, choosing a correct set of features for a specific compiler task remains an ad hoc procedure. In order to guarantee a comprehensive coverage of features, compiler engineers usually need to select excessive number of features. This, unfortunately, would potentially lead to a selection of multiple similar features, which in turn could create a new problem of bias that emphasizes certain aspects of a program’s characteristics, hence reducing the accuracy and performance of the target compiler task. In this paper, we propose FEAture Selection for compilation Tasks (FEAST), an efficient and automated framework for determining the most relevant and representative features from a feature pool. Specifically, FEAST utilizes widely used statistics and machine-learning tools, including LASSO, sequential forward and backward selection, for automatic feature selection, and can in general be applied to any numerical feature set. This paper further proposes an automated approach to compiler parameter assignment for assessing the performance of FEAST. Intensive experimental results demonstrate that, under the compiler parameter assignment task, FEAST can achieve comparable results with about 18% of features that are automatically selected from the entire feature pool. We also inspect these selected features and discuss their roles in program execution.
Feature Sparse PCA
Learning Feature Sparse Principal Components
Feature Squeezing Although deep neural networks (DNNs) have achieved great success in many computer vision tasks, recent studies have shown they are vulnerable to adversarial examples. Such examples, typically generated by adding small but purposeful distortions, can frequently fool DNN models. Previous studies to defend against adversarial examples mostly focused on refining the DNN models. They have either shown limited success or suffer from the expensive computation. We propose a new strategy, \emph{feature squeezing}, that can be used to harden DNN models by detecting adversarial examples. Feature squeezing reduces the search space available to an adversary by coalescing samples that correspond to many different feature vectors in the original space into a single sample. By comparing a DNN model’s prediction on the original input with that on the squeezed input, feature squeezing detects adversarial examples with high accuracy and few false positives. This paper explores two instances of feature squeezing: reducing the color bit depth of each pixel and smoothing using a spatial filter. These strategies are straightforward, inexpensive, and complementary to defensive methods that operate on the underlying model, such as adversarial training.
Feature Store for Machine Learning
Feast (Feature Store) is a tool to manage storage and access of machine learning features. It aims to:
• Support ingesting feature data via batch or streaming
• Provide scalable storage of feature data for serving and training
• Provide an API for low latency access of features
• Enable discovery and documentation of features
• Provide an overview of the general health of features in the system
Introducing Feast
FeATure TransfEr Network
The problem of data augmentation in feature space is considered. A new architecture, denoted the FeATure TransfEr Network (FATTEN), is proposed for the modeling of feature trajectories induced by variations of object pose. This architecture exploits a parametrization of the pose manifold in terms of pose and appearance. This leads to a deep encoder/decoder network architecture, where the encoder factors into an appearance and a pose predictor. Unlike previous attempts at trajectory transfer, FATTEN can be efficiently trained end-to-end, with no need to train separate feature transfer functions. This is realized by supplying the decoder with information about a target pose and the use of a multi-task loss that penalizes category- and pose-mismatches. In result, FATTEN discourages discontinuous or non-smooth trajectories that fail to capture the structure of the pose manifold, and generalizes well on object recognition tasks involving large pose variation. Experimental results on the artificial ModelNet database show that it can successfully learn to map source features to target features of a desired pose, while preserving class identity. Most notably, by using feature space transfer for data augmentation (w.r.t. pose and depth) on SUN-RGBD objects, we demonstrate considerable performance improvements on one/few-shot object recognition in a transfer learning setup, compared to current state-of-the-art methods.
Feature Upsampling CARAFE: Content-Aware ReAssembly of FEatures
Feature, Affinity and Multi-Dimensional Assignment Net
Data association-based multiple object tracking (MOT) involves multiple separated modules processed or optimized differently, which results in complex method design and requires non-trivial tuning of parameters. In this paper, we present an end-to-end model, named FAMNet, where Feature extraction, Affinity estimation and Multi-dimensional assignment are refined in a single network. All layers in FAMNet are designed differentiable thus can be optimized jointly to learn the discriminative features and higher-order affinity model for robust MOT, which is supervised by the loss directly from the assignment ground truth. We also integrate single object tracking technique and a dedicated target management scheme into the FAMNet-based tracking system to further recover false negatives and inhibit noisy target candidates generated by the external detector. The proposed method is evaluated on a diverse set of benchmarks including MOT2015, MOT2017, KITTI-Car and UA-DETRAC, and achieves promising performance on all of them in comparison with state-of-the-arts.
Feature2Mass This paper deals with a method for generating realistic labeled masses. Recently, there have been many attempts to apply deep learning to various bio-image computing fields including computer-aided detection and diagnosis. In order to learn deep network model to be well-behaved in bio-image computing fields, a lot of labeled data is required. However, in many bioimaging fields, the large-size of labeled dataset is scarcely available. Although a few researches have been dedicated to solving this problem through generative model, there are some problems as follows: 1) The generated bio-image does not seem realistic; 2) the variation of generated bio-image is limited; and 3) additional label annotation task is needed. In this study, we propose a realistic labeled bio-image generation method through visual feature processing in latent space. Experimental results have shown that mass images generated by the proposed method were realistic and had wide expression range of targeted mass characteristics.
FeatureAnalytics Ever increasing number of Android malware, has always been a concern for cybersecurity professionals. Even though plenty of anti-malware solutions exist, a rational and pragmatic approach for the same is rare and has to be inspected further. In this paper, we propose a novel two-set feature selection approach based on Rough Set and Statistical Test named as RSST to extract relevant system calls. To address the problem of higher dimensional attribute set, we derived suboptimal system call space by applying the proposed feature selection method to maximize the separability between malware and benign samples. Comprehensive experiments conducted on a dataset consisting of 3500 samples with 30 RSST derived essential system calls resulted in an accuracy of 99.9%, Area Under Curve (AUC) of 1.0, with 1% False Positive Rate (FPR). However, other feature selectors (Information Gain, CFsSubsetEval, ChiSquare, FreqSel and Symmetric Uncertainty) used in the domain of malware analysis resulted in the accuracy of 95.5% with 8.5% FPR. Besides, empirical analysis of RSST derived system calls outperform other attributes such as permissions, opcodes, API, methods, call graphs, Droidbox attributes and network traces.
Feature-based factorized Bilinear Similarity Model
Recommending new items to existing users has remained a challenging problem due to absence of user’s past preferences for these items. The user personalized non-collaborative methods based on item features can be used to address this item cold-start problem. These methods rely on similarities between the target item and user’s previous preferred items. While computing similarities based on item features, these methods overlook the interactions among the features of the items and consider them independently. Modeling interactions among features can be helpful as some features, when considered together, provide a stronger signal on the relevance of an item when compared to case where features are considered independently. To address this important issue, in this work we introduce the Feature-based factorized Bilinear Similarity Model (FBSM), which learns factorized bilinear similarity model for TOP-n recommendation of new items, given the information about items preferred by users in past as well as the features of these items. We carry out extensive empirical evaluations on benchmark datasets, and we find that the proposed FBSM approach improves upon traditional non-collaborative methods in terms of recommendation performance. Moreover, the proposed approach also learns insightful interactions among item features from data, which lead to deep understanding on how these interactions contribute to personalized recommendation.
We consider the problem of ranking a set of items from pairwise comparisons in the presence of features associated with the items. Recent works have established that $O(n\log(n))$ samples are needed to rank well when there is no feature information present. However, this might be sub-optimal in the presence of associated features. We introduce a new probabilistic preference model called feature-Bradley-Terry-Luce (f-BTL) model that generalizes the standard BTL model to incorporate feature information. We present a new least squares based algorithm called fBTL-LS which we show requires much lesser than $O(n\log(n))$ pairs to obtain a good ranking — precisely our new sample complexity bound is of $O(\alpha\log \alpha)$, where $\alpha$ denotes the number of `independent items’ of the set, in general $\alpha << n$. Our analysis is novel and makes use of tools from classical graph matching theory to provide tighter bounds that sheds light on the true complexity of the ranking problem, capturing the item dependencies in terms of their feature representations. This was not possible with earlier matrix completion based tools used for this problem. We also prove an information theoretic lower bound on the required sample complexity for recovering the underlying ranking, which essentially shows the tightness of our proposed algorithms. The efficacy of our proposed algorithms are validated through extensive experimental evaluations on a variety of synthetic and real world datasets.
Feature-Bradley-Terry-Luce Least Squares
Feature-Distributed Stochastic Variance Reduced Gradient
Linear classification has been widely used in many high-dimensional applications like text classification. To perform linear classification for large-scale tasks, we often need to design distributed learning methods on a cluster of multiple machines. In this paper, we propose a new distributed learning method, called feature-distributed stochastic variance reduced gradient (FD-SVRG) for high-dimensional linear classification. Unlike most existing distributed learning methods which are instance-distributed, FD-SVRG is feature-distributed. FD-SVRG has lower communication cost than other instance-distributed methods when the data dimensionality is larger than the number of data instances. Experimental results on real data demonstrate that FD-SVRG can outperform other state-of-the-art distributed methods for high-dimensional linear classification in terms of both communication cost and wall-clock time, when the dimensionality is larger than the number of instances in training data.
FeatureFu FeatureFu contains a collection of library/tools for advanced feature engineering, such as using extended s-expression based feature transformation, to derive features on top of other features, or convert a light weighted model (logistical regression or decision tree) into a feature, in an intuitive way without touching any code.
Feature-Label Memory Network Deep learning typically requires training a very capable architecture using large datasets. However, many important learning problems demand an ability to draw valid inferences from small size datasets, and such problems pose a particular challenge for deep learning. In this regard, various researches on ‘meta-learning’ are being actively conducted. Recent work has suggested a Memory Augmented Neural Network (MANN) for meta-learning. MANN is an implementation of a Neural Turing Machine (NTM) with the ability to rapidly assimilate new data in its memory, and use this data to make accurate predictions. In models such as MANN, the input data samples and their appropriate labels from previous step are bound together in the same memory locations. This often leads to memory interference when performing a task as these models have to retrieve a feature of an input from a certain memory location and read only the label information bound to that location. In this paper, we tried to address this issue by presenting a more robust MANN. We revisited the idea of meta-learning and proposed a new memory augmented neural network by explicitly splitting the external memory into feature and label memories. The feature memory is used to store the features of input data samples and the label memory stores their labels. Hence, when predicting the label of a given input, our model uses its feature memory unit as a reference to extract the stored feature of the input, and based on that feature, it retrieves the label information of the input from the label memory unit. In order for the network to function in this framework, a new memory-writingmodule to encode label information into the label memory in accordance with the meta-learning task structure is designed. Here, we demonstrate that our model outperforms MANN by a large margin in supervised one-shot classification tasks using Omniglot and MNIST datasets.
Feature-Level Domain Adaptation
Domain adaptation is the supervised learning setting in which the training and test data originate from different domains: the so-called source and target domains. In this paper, we propose and study a domain adaption approach, called feature-level domain adaptation (flda), that models the dependence between two domains by means of a feature-level transfer distribution. The domain adapted classifier is trained by minimizing the expected loss under this transfer distribution. Our empirical evaluation of flda focuses on problems with binary and count features in which the domain adaptation can be naturally modeled via a dropout distribution, which allows the final classifier to adapt to the importance of specific features in the target data. Our experimental evaluation suggests that under certain conditions, flda converges to the classifier trained on the target distribution. Experiments with our domain adaptation approach on several real-world problems show that flda performs on par with state-of-the-art techniques in domain adaptation.
Feature-Mover’s Distance
Generative adversarial networks (GANs) have achieved significant success in generating real-valued data. However, the discrete nature of text hinders the application of GAN to text-generation tasks. Instead of using the standard GAN objective, we propose to improve text-generation GAN via a novel approach inspired by optimal transport. Specifically, we consider matching the latent feature distributions of real and synthetic sentences using a novel metric, termed the feature-mover’s distance (FMD). This formulation leads to a highly discriminative critic and easy-to-optimize objective, overcoming the mode-collapsing and brittle-training problems in existing methods. Extensive experiments are conducted on a variety of tasks to evaluate the proposed model empirically, including unconditional text generation, style transfer from non-parallel text, and unsupervised cipher cracking. The proposed model yields superior performance, demonstrating wide applicability and effectiveness.
Feature-Role Normalization Design patterns are elegant and well-tested solutions to recurrent software development problems. They are the result of software developers dealing with problems that frequently occur, solving them in the same or a slightly adapted way. A pattern’s semantics provide the intent, motivation, and applicability, describing what it does, why it is needed, and where it is useful. Consequently, design patterns encode a well of information. Developers weave this information into their systems whenever they use design patterns to solve problems. This work presents Feature Maps, a flexible human- and machine-comprehensible software representation based on micro-structures. Our algorithm, the Feature-Role Normalization, presses the high-dimensional, inhomogeneous vector space of micro-structures into a feature map. We apply these concepts to the problem of detecting instances of design patterns in source code. We evaluate our methodology on four design patterns, a wide range of balanced and imbalanced labeled training data, and compare classical machine learning (Random Forests) with modern deep learning approaches (Convolutional Neural Networks). Feature maps yield robust classifiers even under challenging settings of strongly imbalanced data distributions without sacrificing human comprehensibility. Results suggest that feature maps are an excellent addition in the software analysis toolbox that can reveal useful information hidden in the source code.
Featuretools Featuretools is a framework to perform automated feature engineering. It excels at transforming temporal and relational datasets into feature matrices for machine learning.
Featurized Bidirectional Generative Adversarial Network
Deep neural networks have been demonstrated to be vulnerable to adversarial attacks, where small perturbations are intentionally added to the original inputs to fool the classifier. In this paper, we propose a defense method, Featurized Bidirectional Generative Adversarial Networks (FBGAN), to capture the semantic features of the input and filter the non-semantic perturbation. FBGAN is pre-trained on the clean dataset in an unsupervised manner, adversarially learning a bidirectional mapping between the high-dimensional data space and the low-dimensional semantic space, and mutual information is applied to disentangle the semantically meaningful features. After the bidirectional mapping, the adversarial data can be reconstructed to denoised data, which could be fed into the classifier for classification. We empirically show the quality of reconstruction images and the effectiveness of defense.
Federated Edge Learning
The popularity of mobile devices results in the availability of enormous data and computational resources at the network edge. To leverage the data and resources, a new machine learning paradigm, called edge learning, has emerged where learning algorithms are deployed at the edge for providing fast and intelligent services to mobile users. While computing speeds are advancing rapidly, the communication latency is becoming the bottleneck of fast edge learning. To address this issue, this work is focused on designing a low latency multi-access scheme for edge learning. We consider a popular framework, federated edge learning (FEEL), where edge-server and on-device learning are synchronized to train a model without violating user-data privacy. It is proposed that model updates simultaneously transmitted by devices over broadband channels should be analog aggregated ‘over-the-air’ by exploiting the superposition property of a multi-access channel. Thereby, ‘interference’ is harnessed to provide fast implementation of the model aggregation. This results in dramatical latency reduction compared with the traditional orthogonal access (i.e., OFDMA). In this work, the performance of FEEL is characterized targeting a single-cell random network. First, due to power alignment between devices as required for aggregation, a fundamental tradeoff is shown to exist between the update-reliability and the expected update-truncation ratio. This motivates the design of an opportunistic scheduling scheme for FEEL that selects devices within a distance threshold. This scheme is shown using real datasets to yield satisfactory learning performance in the presence of high mobility. Second, both the multi-access latency of the proposed analog aggregation and the OFDMA scheme are analyzed. Their ratio, which quantifies the latency reduction of the former, is proved to scale almost linearly with device population.
Federated Forest Most real-world data are scattered across different companies or government organizations, and cannot be easily integrated under data privacy and related regulations such as the European Union’s General Data Protection Regulation (GDPR) and China’ Cyber Security Law. Such data islands situation and data privacy & security are two major challenges for applications of artificial intelligence. In this paper, we tackle these challenges and propose a privacy-preserving machine learning model, called Federated Forest, which is a lossless learning model of the traditional random forest method, i.e., achieving the same level of accuracy as the non-privacy-preserving approach. Based on it, we developed a secure cross-regional machine learning system that allows a learning process to be jointly trained over different regions’ clients with the same user samples but different attribute sets, processing the data stored in each of them without exchanging their raw data. A novel prediction algorithm was also proposed which could largely reduce the communication overhead. Experiments on both real-world and UCI data sets demonstrate the performance of the Federated Forest is as accurate as the non-federated version. The efficiency and robustness of our proposed system had been verified. Overall, our model is practical, scalable and extensible for real-life tasks.
Federated Multi-Task Hierarchical Attention Model
Sensors are an integral part of modern Internet of Things (IoT) applications. There is a critical need for the analysis of heterogeneous multivariate temporal data obtained from the individual sensors of these systems. In this paper we particularly focus on the problem of the scarce amount of training data available per sensor. We propose a novel federated multi-task hierarchical attention model (FATHOM) that jointly trains classification/regression models from multiple sensors. The attention mechanism of the proposed model seeks to extract feature representations from the input and learn a shared representation focused on time dimensions across multiple sensors. The underlying temporal and non-linear relationships are modeled using a combination of attention mechanism and long-short term memory (LSTM) networks. We find that our proposed method outperforms a wide range of competitive baselines in both classification and regression settings on activity recognition and environment monitoring datasets. We further provide visualization of feature representations learned by our model at the input sensor level and central time level.
Federated Reinforcement Learning
In reinforcement learning, building policies of high-quality is challenging when the feature space of states is small and the training data is limited. Directly transferring data or knowledge from an agent to another agent will not work due to the privacy requirement of data and models. In this paper, we propose a novel reinforcement learning approach to considering the privacy requirement and building Q-network for each agent with the help of other agents, namely federated reinforcement learning (FRL). To protect the privacy of data and models, we exploit Gausian differentials on the information shared with each other when updating their local models. In the experiment, we evaluate our FRL framework in two diverse domains, Grid-world and Text2Action domains, by comparing to various baselines.
Federated Transfer Learning
Machine learning relies on the availability of a vast amount of data for training. However, in reality, most data are scattered across different organizations and cannot be easily integrated under many legal and practical constraints. In this paper, we introduce a new technique and framework, known as federated transfer learning (FTL), to improve statistical models under a data federation. The federation allows knowledge to be shared without compromising user privacy, and enables complimentary knowledge to be transferred in the network. As a result, a target-domain party can build more flexible and powerful models by leveraging rich labels from a source-domain party. A secure transfer cross validation approach is also proposed to guard the FTL performance under the federation. The framework requires minimal modifications to the existing model structure and provides the same level of accuracy as the non-privacy-preserving approach. This framework is very flexible and can be effectively adapted to various secure multi-party machine learning tasks.
Federated-Autonomous Deep Learning
Electronic health record (EHR) data is collected by individual institutions and often stored across locations in silos. Getting access to these data is difficult and slow due to security, privacy, regulatory, and operational issues. We show, using ICU data from 58 different hospitals, that machine learning models to predict patient mortality can be trained efficiently without moving health data out of their silos using a distributed machine learning strategy. We propose a new method, called Federated-Autonomous Deep Learning (FADL) that trains part of the model using all data sources in a distributed manner and other parts using data from specific data sources. We observed that FADL outperforms traditional federated learning strategy and conclude that balance between global and local training is an important factor to consider when design distributed machine learning methods , especially in healthcare.
FedMark The Web of Data (WoD) has experienced a phenomenal growth in the past. This growth is mainly fueled by tireless volunteers, government subsidies, and open data legislations. The majority of commercial data has not made the transition to the WoD, yet. The problem is that it is not clear how publishers of commercial data can monetize their data in this new setting. Advertisement, which is one of the main financial engines of the World Wide Web, cannot be applied to the Web of Data as such unwanted data can easily be filtered out, automatically. This raises the question how the WoD can (i) maintain its grow when subsidies disappear and (ii) give commercial data providers financial incentives to share their wealth of data. In this paper, we propose a marketplace for the WoD as a solution for this data monetization problem. Our approach allows a customer to transparently buy data from a combination of different providers. To that end, we introduce two different approaches for deciding which data elements to buy and compare their performance. We also introduce FedMark, a prototypical implementation of our marketplace that represents a first step towards an economically viable WoD beyond subsidies.
Feedback Generative Adversarial Network
Generative Adversarial Networks (GANs) represent an attractive and novel approach to generate realistic data, such as genes, proteins, or drugs, in synthetic biology. Here, we apply GANs to generate synthetic DNA sequences encoding for proteins of variable length. We propose a novel feedback-loop architecture, called Feedback GAN (FBGAN), to optimize the synthetic gene sequences for desired properties using an external function analyzer. The proposed architecture also has the advantage that the analyzer need not be differentiable. We apply the feedback-loop mechanism to two examples: 1) generating synthetic genes coding for antimicrobial peptides, and 2) optimizing synthetic genes for the secondary structure of their resulting peptides. A suite of metrics demonstrate that the GAN generated proteins have desirable biophysical properties. The FBGAN architecture can also be used to optimize GAN-generated datapoints for useful properties in domains beyond genomics.
Feedback Networks Currently, the most successful learning models in computer vision are based on learning successive representations followed by a decision layer. This is usually actualized through feedforward multilayer neural networks, e.g. ConvNets, where each layer forms one of such successive representations. However, an alternative that can achieve the same goal is a feedback based approach in which the representation is formed in an iterative manner based on a feedback received from previous iteration’s output. We establish that a feedback based approach has several fundamental advantages over feedforward: it enables making early predictions at the query time, its output naturally conforms to a hierarchical structure in the label space (e.g. a taxonomy), and it provides a new basis for Curriculum Learning. We observe that feedback networks develop a considerably different representation compared to feedforward counterparts, in line with the aforementioned advantages. We put forth a general feedback based learning architecture with the endpoint results on par or better than existing feedforward networks with the addition of the above advantages. We also investigate several mechanisms in feedback architectures (e.g. skip connections in time) and design choices (e.g. feedback length). We hope this study offers new perspectives in quest for more natural and practical learning models.
Feedback Particle Filter
A new formulation of the particle filter for nonlinear filtering is presented, based on concepts from optimal control, and from the mean-field game theory. The optimal control is chosen so that the posterior distribution of a particle matches as closely as possible the posterior distribution of the true state given the observations. This is achieved by introducing a cost function, defined by the Kullback-Leibler (K-L) divergence between the actual posterior, and the posterior of any particle. The optimal control input is characterized by a certain Euler-Lagrange (E-L) equation, and is shown to admit an innovation error-based feedback structure. For diffusions with continuous observations, the value of the optimal control solution is ideal. The two posteriors match exactly, provided they are initialized with identical priors. The feedback particle filter is defined by a family of stochastic systems, each evolving under this optimal control law. A numerical algorithm is introduced and implemented in two general examples, and a neuroscience application involving coupled oscillators. Some preliminary numerical comparisons between the feed- back particle filter and the bootstrap particle filter are described.
Error Analysis of the Stochastic Linear Feedback Particle Filter
Feedforward Neural Network Language Model
The probabilistic feedforward neural network language model has been proposed. It consists of input, projection, hidden and output layers. At the input layer, N previous words are encoded using 1-of-V coding, where V is size of the vocabulary. The input layer is then projected to a projection layer P that has dimensionality ND, using a shared projection matrix. As only N inputs are active at any given time, composition of the projection layer is a relatively cheap operation. The NNLM architecture becomes complex for computation between the projection and the hidden layer, as values in the projection layer are dense. For a common choice of N = 10, the size of the projection layer (P) might be 500 to 2000, while the hidden layer size H is typically 500 to 1000 units. Moreover, the hidden layer is used to compute probability distribution over all the words in the vocabulary, resulting in an output layer with dimensionality V. Thus, the computational complexity per each training example is Q = find + NDH + HV; where the dominating term is HV. However, several practical solutions were proposed for avoiding it; either using hierarchical versions of the softmax, or avoiding normalized models completely by using models that are not normalized during training. With binary tree representations of the vocabulary, the number of output units that need to be evaluated can go down to around log2(V). Thus, most of the complexity is caused by the term NDH.
Feed-Forward Neural Network Lattice Decoding Algorithm Neural network decoding algorithms are recently introduced by Nachmani et al. to decode high-density parity-check (HDPC) codes. In contrast with iterative decoding algorithms such as sum-product or min-sum algorithms in which the weight of each edge is set to $1$, in the neural network decoding algorithms, the weight of every edge depends on its impact in the transmitted codeword. In this paper, we provide a novel \emph{feed-forward neural network lattice decoding algorithm} suitable to decode lattices constructed based on Construction A, whose underlying codes have HDPC matrices. We first establish the concept of feed-forward neural network for HDPC codes and improve their decoding algorithms compared to Nachmani et al. We then apply our proposed decoder for a Construction A lattice with HDPC underlying code, for which the well-known iterative decoding algorithms show poor performances. The main advantage of our proposed algorithm is that instead of assigning and training weights for all edges, which turns out to be time-consuming especially for high-density parity-check matrices, we concentrate on edges which are present in most of $4$-cycles and removing them gives a girth-$6$ Tanner graph. This approach, by slight modifications using updated LLRs instead of initial ones, simultaneously accelerates the training process and improves the error performance of our proposed decoding algorithm.
Feedforward Sequential Memory Networks
We introduce a new structure for memory neural networks, called feedforward sequential memory networks (FSMN), which can learn long-term dependency without using recurrent feedback. The proposed FSMN is a standard feedforward neural networks equipped with learnable sequential memory blocks in the hidden layers. In this work, we have applied FSMN to several language modeling (LM) tasks. Experimental results have shown that the memory blocks in FSMN can learn effective representations of long history. Experiments have shown that FSMN based language models can significantly outperform not only feedforward neural network (FNN) based LMs but also the popular recurrent neural network (RNN) LMs.
FeedRec Recommender systems play a crucial role in our daily lives. Feed streaming mechanism has been widely used in the recommender system, especially on the mobile Apps. The feed streaming setting provides users the interactive manner of recommendation in never-ending feeds. In such an interactive manner, a good recommender system should pay more attention to user stickiness, which is far beyond classical instant metrics, and typically measured by {\bf long-term user engagement}. Directly optimizing the long-term user engagement is a non-trivial problem, as the learning target is usually not available for conventional supervised learning methods. Though reinforcement learning~(RL) naturally fits the problem of maximizing the long term rewards, applying RL to optimize long-term user engagement is still facing challenges: user behaviors are versatile and difficult to model, which typically consists of both instant feedback~(\eg clicks, ordering) and delayed feedback~(\eg dwell time, revisit); in addition, performing effective off-policy learning is still immature, especially when combining bootstrapping and function approximation. To address these issues, in this work, we introduce a reinforcement learning framework — FeedRec to optimize the long-term user engagement. FeedRec includes two components: 1)~a Q-Network which designed in hierarchical LSTM takes charge of modeling complex user behaviors, and 2)~an S-Network, which simulates the environment, assists the Q-Network and voids the instability of convergence in policy learning. Extensive experiments on synthetic data and a real-world large scale data show that FeedRec effectively optimizes the long-term user engagement and outperforms state-of-the-arts.
Fence GAN
Anomaly detection is a classical problem where the aim is to detect anomalous data that do not belong to the normal data distribution. Current state-of-the-art methods for anomaly detection on complex high-dimensional data are based on the generative adversarial network (GAN). However, the traditional GAN loss is not directly aligned with the anomaly detection objective: it encourages the distribution of the generated samples to overlap with the real data and so the resulting discriminator has been found to be ineffective as an anomaly detector. In this paper, we propose simple modifications to the GAN loss such that the generated samples lie at the boundary of the real data distribution. With our modified GAN loss, our anomaly detection method, called Fence GAN (FGAN), directly uses the discriminator score as an anomaly threshold. Our experimental results using the MNIST, CIFAR10 and KDD99 datasets show that Fence GAN yields the best anomaly classification accuracy compared to state-of-the-art methods.
Fence Methods This method is a new class of model selection strategies, for mixed model selection, which includes linear and generalized linear mixed models. The idea involves a procedure to isolate a subgroup of what are known as correct models (of which the optimal model is a member). This is accomplished by constructing a statistical fence, or barrier, to carefully eliminate incorrect models. Once the fence is constructed, the optimal model is selected from among those within the fence according to a criterion which can be made flexible. References: 1. Jiang J., Rao J.S., Gu Z., Nguyen T. (2008), Fence Methods for Mixed Model Selection. The Annals of Statistics, 36(4): 1669-1692. <DOI:10.1214/07-AOS517> <https://…/1216237296>. 2. Jiang J., Nguyen T., Rao J.S. (2009), A Simplified Adaptive Fence Procedure. Statistics and Probability Letters, 79, 625-629. <DOI:10.1016/j.spl.2008.10.014> <https://…A_simplified_adaptive_fence_procedure> 3. Jiang J., Nguyen T., Rao J.S. (2010), Fence Method for Nonparametric Small Area Estimation. Survey Methodology, 36(1), 3-11. <http://…/12-001-x2010001-eng.pdf>. 4. Jiming Jiang, Thuan Nguyen and J. Sunil Rao (2011), Invisible fence methods and the identification of differentially expressed gene sets. Statistics and Its Interface, Volume 4, 403-415. <http://…/SII-2011-0004-0003-a014.pdf>. 5. Thuan Nguyen & Jiming Jiang (2012), Restricted fence method for covariate selection in longitudinal data analysis. Biostatistics, 13(2), 303-314. <DOI:10.1093/biostatistics/kxr046> <https://…ce-method-for-covariate-selection-in>. 6. Thuan Nguyen, Jie Peng, Jiming Jiang (2014), Fence Methods for Backcross Experiments. Statistical Computation and Simulation, 84(3), 644-662. <DOI:10.1080/00949655.2012.721885> <https://…/>. 7. Jiang, J. (2014), The fence methods, in Advances in Statistics, Hindawi Publishing Corp., Cairo. <DOI:10.1155/2014/830821>. 8. Jiming Jiang and Thuan Nguyen (2015), The Fence Methods, World Scientific, Singapore. <https://…/plp>.
Fenchel Lifted Network Despite the recent successes of deep neural networks, the corresponding training problem remains highly non-convex and difficult to optimize. Classes of models have been proposed that introduce greater structure to the objective function at the cost of lifting the dimension of the problem. However, these lifted methods sometimes perform poorly compared to traditional neural networks. In this paper, we introduce a new class of lifted models, Fenchel lifted networks, that enjoy the same benefits as previous lifted models, without suffering a degradation in performance over classical networks. Our model represents activation functions as equivalent biconvex constraints and uses Lagrange Multipliers to arrive at a rigorous lower bound of the traditional neural network training problem. This model is efficiently trained using block-coordinate descent and is parallelizable across data points and/or layers. We compare our model against standard fully connected and convolutional networks and show that we are able to match or beat their performance.
Fenwick Tree A Fenwick tree or binary indexed tree is a data structure that can efficiently update elements and calculate prefix sums in a table of numbers. This structure was proposed by Peter Fenwick in 1994 to improve the efficiency of arithmetic coding compression algorithms. When compared with a flat array of numbers, the Fenwick tree achieves a much better balance between two operations: element update and prefix sum calculation. In a flat array of {\displaystyle n} n numbers, you can either store the elements, or the prefix sums. In the first case, computing prefix sums requires linear time; in the second case, updating the array elements requires linear time (in both cases, the other operation can be performed in constant time). Fenwick trees allow both operations to be performed in {\displaystyle O(\log n)} O(\log n) time. This is achieved by representing the numbers as a tree, where the value of each node is the sum of the numbers in that subtree. The tree structure allows operations to be performed using only {\displaystyle O(\log n)} O(\log n) node accesses.
FermiNet The tremendous potential exhibited by deep learning is often offset by architectural and computational complexity, making widespread deployment a challenge for edge scenarios such as mobile and other consumer devices. To tackle this challenge, we explore the following idea: Can we learn generative machines to automatically generate deep neural networks with efficient network architectures? In this study, we introduce the idea of generative synthesis, which is premised on the intricate interplay between a generator-inquisitor pair that work in tandem to garner insights and learn to generate highly efficient deep neural networks that best satisfies operational requirements. What is most interesting is that, once a generator has been learned through generative synthesis, it can be used to generate not just one but a large variety of different, unique highly efficient deep neural networks that satisfy operational requirements. Experimental results for image classification, semantic segmentation, and object detection tasks illustrate the efficacy of generative synthesis in producing generators that automatically generate highly efficient deep neural networks (which we nickname FermiNets) with higher model efficiency and lower computational costs (reaching >10x more efficient and fewer multiply-accumulate operations than several tested state-of-the-art networks), as well as higher energy efficiency (reaching >4x improvements in image inferences per joule consumed on a Nvidia Tegra X2 mobile processor). As such, generative synthesis can be a powerful, generalized approach for accelerating and improving the building of deep neural networks for on-device edge scenarios.
Feudal Multi-agent Hierarchies
We investigate how reinforcement learning agents can learn to cooperate. Drawing inspiration from human societies, in which successful coordination of many individuals is often facilitated by hierarchical organisation, we introduce Feudal Multi-agent Hierarchies (FMH). In this framework, a ‘manager’ agent, which is tasked with maximising the environmentally-determined reward function, learns to communicate subgoals to multiple, simultaneously-operating, ‘worker’ agents. Workers, which are rewarded for achieving managerial subgoals, take concurrent actions in the world. We outline the structure of FMH and demonstrate its potential for decentralised learning and control. We find that, given an adequate set of subgoals from which to choose, FMH performs, and particularly scales, substantially better than cooperative approaches that use a shared reward function.
FeUdal Networks
We introduce FeUdal Networks (FuNs): a novel architecture for hierarchical reinforcement learning. Our approach is inspired by the feudal reinforcement learning proposal of Dayan and Hinton, and gains power and efficacy by decoupling end-to-end learning across multiple levels — allowing it to utilise different resolutions of time. Our framework employs a Manager module and a Worker module. The Manager operates at a lower temporal resolution and sets abstract goals which are conveyed to and enacted by the Worker. The Worker generates primitive actions at every tick of the environment. The decoupled structure of FuN conveys several benefits — in addition to facilitating very long timescale credit assignment it also encourages the emergence of sub-policies associated with different goals set by the Manager. These properties allow FuN to dramatically outperform a strong baseline agent on tasks that involve long-term credit assignment or memorisation. We demonstrate the performance of our proposed system on a range of tasks from the ATARI suite and also from a 3D DeepMind Lab environment.
Few-Shot Adaptive Faster-RCNN
To mitigate the detection performance drop caused by domain shift, we aim to develop a novel few-shot adaptation approach that requires only a few target domain images with limited bounding box annotations. To this end, we first observe several significant challenges. First, the target domain data is highly insufficient, making most existing domain adaptation methods ineffective. Second, object detection involves simultaneous localization and classification, further complicating the model adaptation process. Third, the model suffers from over-adaptation (similar to overfitting when training with a few data example) and instability risk that may lead to degraded detection performance in the target domain. To address these challenges, we first introduce a pairing mechanism over source and target features to alleviate the issue of insufficient target domain samples. We then propose a bi-level module to adapt the source trained detector to the target domain: 1) the split pooling based image level adaptation module uniformly extracts and aligns paired local patch features over locations, with different scale and aspect ratio; 2) the instance level adaptation module semantically aligns paired object features while avoids inter-class confusion. Meanwhile, a source model feature regularization (SMFR) is applied to stabilize the adaptation process of the two modules. Combining these contributions gives a novel few-shot adaptive Faster-RCNN framework, termed FAFRCNN, which effectively adapts to target domain with a few labeled samples. Experiments with multiple datasets show that our model achieves new state-of-the-art performance under both the interested few-shot domain adaptation(FDA) and unsupervised domain adaptation(UDA) setting.
Few-Shot Classification In few-shot classification a classifier must generalize to new classes not seen in the training set, given only a small number of examples of each new class.
“One-Shot Learning”
Few-Shot Self Reminder
Deep neural networks are known to suffer the catastrophic forgetting problem, where they tend to forget the knowledge from the previous tasks when sequentially learning new tasks. Such failure hinders the application of deep learning based vision system in continual learning settings. In this work, we present a simple yet surprisingly effective way of preventing catastrophic forgetting. Our method, called Few-shot Self Reminder (FSR), regularizes the neural net from changing its learned behaviour by performing logit matching on selected samples kept in episodic memory from the old tasks. Surprisingly, this simplistic approach only requires to retrain a small amount of data in order to outperform previous methods in knowledge retention. We demonstrate the superiority of our method to the previous ones in two different continual learning settings on popular benchmarks, as well as a new continual learning problem where tasks are designed to be more dissimilar.
FIA Latent factor models (LFMs) such as matrix factorization achieve the state-of-the-art performance among various Collaborative Filtering (CF) approaches for recommendation. Despite the high recommendation accuracy of LFMs, a critical issue to be resolved is the lack of explainability. Extensive efforts have been made in the literature to incorporate explainability into LFMs. However, they either rely on auxiliary information which may not be available in practice, or fail to provide easy-to-understand explanations. In this paper, we propose a fast influence analysis method named FIA, which successfully enforces explicit neighbor-style explanations to LFMs with the technique of influence functions stemmed from robust statistics. We first describe how to employ influence functions to LFMs to deliver neighbor-style explanations. Then we develop a novel influence computation algorithm for matrix factorization with high efficiency. We further extend it to the more general neural collaborative filtering and introduce an approximation algorithm to accelerate influence analysis over neural network models. Experimental results on real datasets demonstrate the correctness, efficiency and usefulness of our proposed method.
Fidelity-Weighted Learning
Training deep neural networks requires many training samples, but in practice training labels are expensive to obtain and may be of varying quality, as some may be from trusted expert labelers while others might be from heuristics or other sources of weak supervision such as crowd-sourcing. This creates a fundamental quality versus-quantity trade-off in the learning process. Do we learn from the small amount of high-quality data or the potentially large amount of weakly-labeled data? We argue that if the learner could somehow know and take the label-quality into account when learning the data representation, we could get the best of both worlds. To this end, we propose ‘fidelity-weighted learning’ (FWL), a semi-supervised student-teacher approach for training deep neural networks using weakly-labeled data. FWL modulates the parameter updates to a student network (trained on the task we care about) on a per-sample basis according to the posterior confidence of its label-quality estimated by a teacher (who has access to the high-quality labels). Both student and teacher are learned from the data. We evaluate FWL on two tasks in information retrieval and natural language processing where we outperform state-of-the-art alternative semi-supervised methods, indicating that our approach makes better use of strong and weak labels, and leads to better task-dependent data representations.
Fiducial Inference Fiducial inference is one of a number of different types of statistical inference. These are rules, intended for general application, by which conclusions can be drawn from samples of data. In modern statistical practice, attempts to work with fiducial inference have fallen out of fashion in favour of frequentist inference, Bayesian inference and decision theory. However, fiducial inference is important in the history of statistics since its development led to the parallel development of concepts and tools in theoretical statistics that are widely used. Some current research in statistical methodology is either explicitly linked to fiducial inference or is closely connected to it.
Multivariate Subjective Fiducial Inference
Field Attentive Deep Field-aware Factorization Machine
Click through rate (CTR) estimation is a fundamental task in personalized advertising and recommender systems. Recent years have witnessed the success of both the deep learning based model and attention mechanism in various tasks in computer vision (CV) and natural language processing (NLP). How to combine the attention mechanism with deep CTR model is a promising direction because it may ensemble the advantages of both sides. Although some CTR model such as Attentional Factorization Machine (AFM) has been proposed to model the weight of second order interaction features, we posit the evaluation of feature importance before explicit feature interaction procedure is also important for CTR prediction tasks because the model can learn to selectively highlight the informative features and suppress less useful ones if the task has many input features. In this paper, we propose a new neural CTR model named Field Attentive Deep Field-aware Factorization Machine (FAT-DeepFFM) by combining the Deep Field-aware Factorization Machine (DeepFFM) with Compose-Excitation network (CENet) field attention mechanism which is proposed by us as an enhanced version of Squeeze-Excitation network (SENet) to highlight the feature importance. We conduct extensive experiments on two real-world datasets and the experiment results show that FAT-DeepFFM achieves the best performance and obtains different improvements over the state-of-the-art methods. We also compare two kinds of attention mechanisms (attention before explicit feature interaction vs. attention after explicit feature interaction) and demonstrate that the former one outperforms the latter one significantly.
Field-aware Factorization Machines
Field-aware factorization machines (FFM) have been used to win two click-through rate prediction competitions hosted by Criteo and Avazu. In these slides we introduce the formulation of FFM together with well known linear model, degree-2 polynomial model, and factorization machines.
Field-aware Neural Factorization Machine
Recommendation systems and computing advertisements have gradually entered the field of academic research from the field of commercial applications. Click-through rate prediction is one of the core research issues because the prediction accuracy affects the user experience and the revenue of merchants and platforms. Feature engineering is very important to improve click-through rate prediction. Traditional feature engineering heavily relies on people’s experience, and is difficult to construct a feature combination that can describe the complex patterns implied in the data. This paper combines traditional feature combination methods and deep neural networks to automate feature combinations to improve the accuracy of click-through rate prediction. We propose a mechannism named ‘Field-aware Neural Factorization Machine’ (FNFM). This model can have strong second order feature interactive learning ability like Field-aware Factorization Machine, on this basis, deep neural network is used for higher-order feature combination learning. Experiments show that the model has stronger expression ability than current deep learning feature combination models like the DeepFM, DCN and NFM.
FiloDB FiloDB is a new open-source distributed, versioned, and columnar analytical database designed for modern streaming workloads.
· Distributed – FiloDB is designed from the beginning to run on best-of-breed distributed, scale-out storage platforms such as Apache Cassandra. Queries run in parallel in Apache Spark for scale-out ad-hoc analysis.
· Columnar – FiloDB brings breakthrough performance levels for analytical queries by using a columnar storage layout with different space-saving techniques like dictionary compression. True columnar querying techniques are on the roadmap. The current performance is comparable to Parquet, and one to two orders of magnitude faster than Spark on Cassandra 2.x for analytical queries. For the POC performance comparison, please see cassandra-gdelt repo.
· Versioned – At the same time, row-level, column-level operations and built in versioning gives FiloDB far more flexibility than can be achieved using file-based technologies like Parquet alone.
· Designed for streaming – Enable easy exactly-once ingestion from Kafka for streaming events, time series, and IoT applications – yet enable extremely fast ad-hoc analysis using the ease of use of SQL. Each row is keyed by a partition and sort key, and writes using the same key are idempotent. FiloDB does the hard work of keeping data stored in an efficient and sorted format.
FiloDB is easy to use! You can use Spark SQL for both ingestion (including from Streaming!) and querying.
Connect Tableau or any other JDBC analysis tool to Spark SQL, and easily ingest data from any source with Spark support(JSON, CSV, traditional database, Kafka, etc.)
FiloDB is a great fit for bulk analytical workloads, or streaming / event data. It is not optimized for heavily transactional, update-oriented workflows.
Introducing FiloDB
Filter Bubble A filter bubble is a result of a personalized search in which a website algorithm selectively guesses what information a user would like to see based on information about the user (such as location, past click behavior and search history) and, as a result, users become separated from information that disagrees with their viewpoints, effectively isolating them in their own cultural or ideological bubbles. Prime examples are Google Personalized Search results and Facebook’s personalized news stream. The term was coined by internet activist Eli Pariser in his book by the same name; according to Pariser, users get less exposure to conflicting viewpoints and are isolated intellectually in their own informational bubble. Pariser related an example in which one user searched Google for “BP” and got investment news about British Petroleum while another searcher got information about the Deepwater Horizon oil spill and that the two search results pages were “strikingly different”. The bubble effect may have negative implications for civic discourse, according to Pariser, but there are contrasting views suggesting the effect is minimal and addressable.
Filtering Variational Objectives
The evidence lower bound (ELBO) appears in many algorithms for maximum likelihood estimation (MLE) with latent variables because it is a sharp lower bound of the marginal log-likelihood. For neural latent variable models, optimizing the ELBO jointly in the variational posterior and model parameters produces state-of-the-art results. Inspired by the success of the ELBO as a surrogate MLE objective, we consider the extension of the ELBO to a family of lower bounds defined by a Monte Carlo estimator of the marginal likelihood. We show that the tightness of such bounds is asymptotically related to the variance of the underlying estimator. We introduce a special case, the filtering variational objectives (FIVOs), which takes the same arguments as the ELBO and passes them through a particle filter to form a tighter bound. FIVOs can be optimized tractably with stochastic gradients, and are particularly suited to MLE in sequential latent variable models. In standard sequential generative modeling tasks we present uniform improvements over models trained with ELBO, including some whole nat-per-timestep improvements.
FinBrain Artificial intelligence (AI) is the core technology of technological revolution and industrial transformation. As one of the new intelligent needs in the AI 2.0 era, financial intelligence has elicited much attention from the academia and industry. In our current dynamic capital market, financial intelligence demonstrates a fast and accurate machine learning capability to handle complex data and has gradually acquired the potential to become a ‘financial brain’. In this work, we survey existing studies on financial intelligence. First, we describe the concept of financial intelligence and elaborate on its position in the financial technology field. Second, we introduce the development of financial intelligence and review state-of-the-art techniques in wealth management, risk management, financial security, financial consulting, and blockchain. Finally, we propose a research framework called FinBrain and summarize four open issues, namely, explainable financial agents and causality, perception and prediction under uncertainty, risk-sensitive and robust decision making, and multi-agent game and mechanism design. We believe that these research directions can lay the foundation for the development of AI 2.0 in the finance field.
Fine-Grained Pattern Matching Processing of streaming time series data from sensors with lower latency and limited computing resource comes to a critical problem as the growth of Industry 4.0 and Industry Internet of Things(IIoT). To tackle the real world challenge in this area, like equipment health monitoring by comparing the incoming data stream with known fault patterns, we formulate a new problem, called ‘fine-grained pattern matching’. It allows users to define varied deviations to different segments of a given pattern, and fuzzy breakpoint of adjunct segments, which urges the dramatically increased complexity against traditional pattern matching problem over stream. In this paper, we propose a novel 2-phase approach to solve this problem. In pruning phase, we propose ELB(Equal Length Block) Representation and BSP (Block-Skipping Pruning) policy, which efficiently filter the unmatched subsequence with the guarantee of no-false dismissals. In post-processing phase, we provide an algorithm to further examine the possible matches in linear complexity. We conducted an extensive experimental evaluation on synthetic and real-world datasets, which illustrates that our algorithm outperforms the brute-force method and MSM, a multi-step filter mechanism over the multi-scaled representation, by orders of magnitude.
Fine-Tuned Language Model
Transfer learning has revolutionized computer vision, but existing approaches in NLP still require task-specific modifications and training from scratch. We propose Fine-tuned Language Models (FitLaM), an effective transfer learning method that can be applied to any task in NLP, and introduce techniques that are key for fine-tuning a state-of-the-art language model. Our method significantly outperforms the state-of-the-art on five text classification tasks, reducing the error by 18-24% on the majority of datasets. We open-source our pretrained models and code to enable adoption by the community.
Finite Element Duality-Based Inexact Majorized Accelerating Block Coordinate Descent
In this paper, elliptic control problems with integral constraint on the gradient of the state and box constraints on the control are considered. The optimal conditions of the problem are proved. To numerically solve the problem, we use the ‘First discretize, then optimize’ approach. Specifically, we discretize both the state and the control by piecewise linear functions. To solve the discretized problem efficiently, we first transform it into a multi-block unconstrained convex optimization problem via its dual, then we extend the inexact majorized accelerating block coordinate descent (imABCD) algorithm to solve it. The entire algorithm framework is called finite element duality-based inexact majorized accelerating block coordinate descent (FE-dABCD) algorithm. Thanks to the inexactness of the FE-dABCD algorithm, each subproblems are allowed to be solved inexactly. For the smooth subproblem, we use the generalized minimal residual (GMRES) method with preconditioner to slove it. For the nonsmooth subproblems, one of them has a closed form solution through introducing appropriate proximal term, another is solved combining semi-smooth Newton (SSN) method. Based on these efficient strategies, we prove that our proposed FE-dABCD algorithm enjoys $O(\frac{1}{k^2})$ iteration complexity. Some numerical experiments are done and the numerical results show the efficiency of the FE-dABCD algorithm.
Finite First-Order Theory We present the finite first-order theory (FFOT) machine, which provides an atemporal description of computation. We then develop a concept of complexity for the FFOT machine, and prove that the class of problems decidable by a FFOT machine with polynomial resources is NP intersect co-NP.
Finite Primitiveness Finite Primitiveness’ by Mauldin and Urbanski.
Firebreak Decision Problem Suppose we have a network that is represented by a graph $G$. Potentially a fire (or other type of contagion) might erupt at some vertex of $G$. We are able to respond to this outbreak by establishing a firebreak at $k$ other vertices of $G$, so that the fire cannot pass through these fortified vertices. The question that now arises is which $k$ vertices will result in the greatest number of vertices being saved from the fire, assuming that the fire will spread to every vertex that is not fully behind the $k$ vertices of the firebreak. This is the essence of the Firebreak decision problem.
FIRE-DES++ Despite being very effective in several classification tasks, Dynamic Ensemble Selection (DES) techniques can select classifiers that classify all samples in the region of competence as being from the same class. The Frienemy Indecision REgion DES (FIRE-DES) tackles this problem by pre-selecting classifiers that correctly classify at least one pair of samples from different classes in the region of competence of the test sample. However, FIRE-DES applies the pre-selection for the classification of a test sample if and only if its region of competence is composed of samples from different classes (indecision region), even though this criterion is not reliable for determining if a test sample is located close to the borders of classes (true indecision region) when the region of competence is obtained using classical nearest neighbors approach. Because of that, FIRE-DES mistakes noisy regions for true indecision regions, leading to the pre-selection of incompetent classifiers, and mistakes true indecision regions for safe regions, leaving samples in such regions without any pre-selection. To tackle these issues, we propose the FIRE-DES++, an enhanced FIRE-DES that removes noise and reduces the overlap of classes in the validation set; and defines the region of competence using an equal number of samples of each class, avoiding selecting a region of competence with samples of a single class. Experiments are conducted using FIRE-DES++ with 8 different dynamic selection techniques on 64 classification datasets. Experimental results show that FIRE-DES++ increases the classification performance of all DES techniques considered in this work, outperforming FIRE-DES with 7 out of the 8 DES techniques, and outperforming state-of-the-art DES frameworks.
Firefighter Problem The dynamics of infectious diseases spread is crucial in determining their risk and offering ways to contain them. We study sequential vaccination of individuals in networks. In the original (deterministic) version of the Firefighter problem, a fire breaks out at some node of a given graph. At each time step, b nodes can be protected by a firefighter and then the fire spreads to all unprotected neighbors of the nodes on fire. The process ends when the fire can no longer spread. We extend the Firefighter problem to a probabilistic setting, where the infection is stochastic. We devise a simple policy that only vaccinates neighbors of infected nodes and is optimal on regular trees and on general graphs for a sufficiently large budget. We derive methods for calculating upper and lower bounds of the expected number of infected individuals, as well as provide estimates on the budget needed for containment in expectation. We calculate these explicitly on trees, d-dimensional grids, and Erd\H{o}s R\'{e}nyi graphs. Finally, we construct a state-dependent budget allocation strategy and demonstrate its superiority over constant budget allocation on real networks following a first order acquaintance vaccination policy.
Firefly Algorithm
The firefly algorithm (FA) is a metaheuristic algorithm, inspired by the flashing behaviour of fireflies. The primary purpose for a firefly’s flash is to act as a signal system to attract other fireflies. Xin-She Yang formulated this firefly algorithm by assuming:
1.All fireflies are unisexual, so that one firefly will be attracted to all other fireflies;
2.Attractiveness is proportional to their brightness, and for any two fireflies, the less bright one will be attracted by (and thus move to) the brighter one; however, the brightness can decrease as their distance increases;
3.If there are no fireflies brighter than a given firefly, it will move randomly.
The brightness should be associated with the objective function. Firefly algorithm is a nature-inspired metaheuristic optimization algorithm.
First Story Detection
Given a series of documents, first story is defined as the first document to discuss a specific event, which occurred at a particular time and place. First story detection (FSD) was firstly defined byAllan in 2002 in terms of topic detection and tracking.
“Novelty Detection”
“Topic Detection and Tracking”
FISH Time-evolving stream datasets exist ubiquitously in many real-world applications where their inherent hot keys often evolve over times. Nevertheless, few existing solutions can provide efficient load balance on these time-evolving datasets while preserving low memory overhead. In this paper, we present a novel grouping approach (named FISH), which can provide the efficient time-evolving stream processing at scale. The key insight of this work is that the keys of time-evolving stream data can have a skewed distribution within any bounded distance of time interval. This enables to accurately identify the recent hot keys for the real-time load balance within a bounded scope. We therefore propose an epoch-based recent hot key identification with specialized intra-epoch frequency counting (for maintaining low memory overhead) and inter-epoch hotness decaying (for suppressing superfluous computation). We also propose to heuristically infer the accurate information of remote workers through computation rather than communication for cost-efficient worker assignment. We have integrated our approach into Apache Storm. Our results on a cluster of 128 nodes for both synthetic and real-world stream datasets show that FISH significantly outperforms state-of-the-art with the average and the 99th percentile latency reduction by 87.12% and 76.34% (vs. W-Choices), and memory overhead reduction by 99.96% (vs. Shuffle Grouping).
Fisher Vector encoding with Variational Auto-Encoder
Deep convolutional neural networks (CNNs) have proven highly effective for visual recognition, where learning a universal representation from activations of convolutional layer plays a fundamental problem. In this paper, we present Fisher Vector encoding with Variational Auto-Encoder (FV-VAE), a novel deep architecture that quantizes the local activations of convolutional layer in a deep generative model, by training them in an end-to-end manner. To incorporate FV encoding strategy into deep generative models, we introduce Variational Auto-Encoder model, which steers a variational inference and learning in a neural network which can be straightforwardly optimized using standard stochastic gradient method. Different from the FV characterized by conventional generative models (e.g., Gaussian Mixture Model) which parsimoniously fit a discrete mixture model to data distribution, the proposed FV-VAE is more flexible to represent the natural property of data for better generalization. Extensive experiments are conducted on three public datasets, i.e., UCF101, ActivityNet, and CUB-200-2011 in the context of video action recognition and fine-grained image classification, respectively. Superior results are reported when compared to state-of-the-art representations. Most remarkably, our proposed FV-VAE achieves to-date the best published accuracy of 94.2% on UCF101.
Fisher-Bures Adversary Graph Convolutional Network In a graph convolutional network, we assume that the graph $G$ is generated with respect to some observation noise. We make small random perturbations $\Delta{}G$ of the graph and try to improve generalization. Based on quantum information geometry, we can have quantitative measurements on the scale of $\Delta{}G$. We try to maximize the intrinsic scale of the permutation with a small budget while minimizing the loss based on the perturbed $G+\Delta{G}$. Our proposed model can consistently improve graph convolutional networks on semi-supervised node classification tasks with reasonable computational overhead. We present two different types of geometry on the manifold of graphs: one is for measuring the intrinsic change of a graph; the other is for measuring how such changes can affect externally a graph neural network. These new analytical tools will be useful in developing a good understanding of graph neural networks and fostering new techniques.
Five Pillars of Artificial Intelligence Research
In this article, we provide and overview of what we consider to be some of the most pressing research questions facing the field of artificial intelligence (AI); as well as its sub-field of computational intelligence (CI). We demarcate these questions using five unique Rs – namely,
(i) Rationalizability,
(ii) Resilience,
(iii) Reproducibility,
(iv) Realism, and
(v) Responsibility.
Just as air serves as the basic element of biological life, the term AIR5 – cumulatively referring to the five aforementioned Rs – is introduced herein to mark some of the basic elements of artificial life (supporting the sustained growth of AI and CI). A brief summary of each of the Rs is presented, highlighting their relevance as pillars of future research in this arena.
Fixed Effects Model In econometrics and statistics, a fixed effects model is a statistical model that represents the observed quantities in terms of explanatory variables that are treated as if the quantities were non-random. This is in contrast to random effects models and mixed models in which either all or some of the explanatory variables are treated as if they arise from random causes. Contrast this to the biostatistics definitions, as biostatisticians use “fixed” and “random” effects to respectively refer to the population-average and subject-specific effects (and where the latter are generally assumed to be unknown, latent variables). Often the same structure of model, which is usually a linear regression model, can be treated as any of the three types depending on the analyst’s viewpoint, although there may be a natural choice in any given situation.
Fixed-Point Factorized Networks
In recent years, Deep Neural Networks (DNNs) based methods have achieved remarkable performance in a wide range of tasks and have been among the most powerful and widely used techniques in computer vision, speech recognition and Natural Language Processing. However, DNN-based methods are both computational-intensive and resource-consuming, which hinders the application of these methods on embedded systems like smart phones. To alleviate this problem, we introduce a novel Fixed-point Factorized Networks (FFN) on pre-trained models to reduce the computational complexity as well as the storage requirement of networks. Extensive experiments on large-scale ImageNet classification task show the effectiveness of our proposed method.
Fixed-Size Ordinally Forgetting Encoding
Question answering over knowledge base (KB-QA) has recently become a popular research topic in NLP. One popular way to solve the KB-QA problem is to make use of a pipeline of several NLP modules, including entity discovery and linking (EDL) and relation detection. Recent success on KB-QA task usually involves complex network structures with sophisticated heuristics. Inspired by a previous work that builds a strong KB-QA baseline, we propose a simple but general neural model composed of fixed-size ordinally forgetting encoding (FOFE) and deep neural networks, called FOFE-net to solve KB-QA problem at different stages. For evaluation, we use two popular KB-QA datasets, SimpleQuestions and WebQSP, and a newly created dataset, FreebaseQA. The experimental results show that FOFE-net performs well on KB-QA subtasks, entity discovery and linking (EDL) and relation detection, and in turn pushing overall KB-QA system to achieve strong results on all datasets.
FixyNN The computational demands of computer vision tasks based on state-of-the-art Convolutional Neural Network (CNN) image classification far exceed the energy budgets of mobile devices. This paper proposes FixyNN, which consists of a fixed-weight feature extractor that generates ubiquitous CNN features, and a conventional programmable CNN accelerator which processes a dataset-specific CNN. Image classification models for FixyNN are trained end-to-end via transfer learning, with the common feature extractor representing the transfered part, and the programmable part being learnt on the target dataset. Experimental results demonstrate FixyNN hardware can achieve very high energy efficiencies up to 26.6 TOPS/W ($4.81 \times$ better than iso-area programmable accelerator). Over a suite of six datasets we trained models via transfer learning with an accuracy loss of $<1\%$ resulting in up to 11.2 TOPS/W – nearly $2 \times$ more efficient than a conventional programmable CNN accelerator of the same area.
In this paper, we propose a test, called Flagged-1-Bit (F1B) test, to study the intrinsic capability of recurrent neural networks in sequence learning. Four different recurrent network models are studied both analytically and experimentally using this test. Our results suggest that in general there exists a conflict between feature selection and feature memorization in sequence learning. Such a conflict can be resolved either using a gating mechanism as in LSTM, or by increasing the state dimension as in Vanilla RNN. Gated models resolve this conflict by adaptively adjusting their state-update equations, whereas Vanilla RNN resolves this conflict by assigning different dimensions different tasks. Insights into feature selection and memorization in recurrent networks are given.
Flair A very simple framework for state-of-the-art Natural Language Processing (NLP)
Flat Clustering and Topic Modeling based on Fast Rank-2 NMF
The importance of unsupervised clustering and topic modeling is well recognized with ever-increasing volumes of text data. In this paper, we propose a fast method for hierarchical clustering and topic modeling called HierNMF2. Our method is based on fast Rank-2 nonnegative matrix factorization (NMF) that performs binary clustering and an efficient node splitting rule. Further utilizing the final leaf nodes generated in HierNMF2 and the idea of nonnegative least squares fitting, we propose a new clustering/topic modeling method called FlatNMF2 that recovers a flat clustering/topic modeling result in a very simple yet significantly more effective way than any other existing methods. We describe highly optimized open source software in C++ for both HierNMF2 and FlatNMF2 for hierarchical and partitional clustering/topic modeling of document data sets. Substantial experimental tests are presented that illustrate significant improvements both in computational time as well as quality of solutions. We compare our methods to other clustering methods including K-means, standard NMF, and CLUTO, and also topic modeling methods including latent Dirichlet allocation (LDA) and recently proposed algorithms for NMF with separability constraints. Overall, we present efficient tools for analyzing large-scale data sets, and techniques that can be generalized to many other data analytics problem domains.
Flatland Paradox “Stone’s Paradox”
FlexEncoder Recommender systems have recently attracted many researchers in the deep learning community. The state-of-the-art deep neural network models used in recommender systems are typically multilayer perceptron and deep Autoencoder (DAE), among which DAE usually shows better performance due to its superior capability to reconstruct the inputs. However, we found existing DAE recommendation systems that have similar implementations on similar datasets result in vastly different parameter settings. In this work, we have built a flexible DAE model, named FlexEncoder that uses configurable parameters and unique features to analyse the parameter influences on the prediction accuracy of recommender systems. This will help us identify the best-performance parameters given a dataset. Extensive evaluation on the MovieLens datasets are conducted, which drives our conclusions on the influences of DAE parameters. Specifically, we find that DAE parameters strongly affect the prediction accuracy of the recommender systems, and the effect is transferable to similar datasets in a larger size. We open our code to public which could benefit both new users for DAE — they can quickly understand how DAE works for recommendation systems, and experienced DAE users — it easier for them to tune the parameters on different datasets.
FlexFlow “Sample, Operation, Attribute, and Parameter Dimensions”
Flexible Attributed Network Embedding
Network embedding aims to find a way to encode network by learning an embedding vector for each node in the network. The network often has property information which is highly informative with respect to the node’s position and role in the network. Most network embedding methods fail to utilize this information during network representation learning. In this paper, we propose a novel framework, FANE, to integrate structure and property information in the network embedding process. In FANE, we design a network to unify heterogeneity of the two information sources, and define a new random walking strategy to leverage property information and make the two information compensate. FANE is conceptually simple and empirically powerful. It improves over the state-of-the-art methods on Cora dataset classification task by over 5%, more than 10% on WebKB dataset classification task. Experiments also show that the results improve more than the state-of-the-art methods as increasing training size. Moreover, qualitative visualization show that our framework is helpful in network property information exploration. In all, we present a new way for efficiently learning state-of-the-art task-independent representations in complex attributed networks. The source code and datasets of this paper can be obtained from https://…/FANE.
Flexible Clustered Lifelong Learning
Consider the lifelong learning paradigm whose objective is to learn a sequence of tasks depending on previous experiences, e.g., knowledge library or deep network weights. However, the knowledge libraries or deep networks for most recent lifelong learning models are with prescribed size, and can degenerate the performance for both learned tasks and coming ones when facing with a new task environment (cluster). To address this challenge, we propose a novel incremental clustered lifelong learning framework with two knowledge libraries: feature learning library and model knowledge library, called Flexible Clustered Lifelong Learning (FCL3). Specifically, the feature learning library modeled by an autoencoder architecture maintains a set of representation common across all the observed tasks, and the model knowledge library can be self-selected by identifying and adding new representative models (clusters). When a new task arrives, our proposed FCL3 model firstly transfers knowledge from these libraries to encode the new task, i.e., effectively and selectively soft-assigning this new task to multiple representative models over feature learning library. Then, 1) the new task with a higher outlier probability will then be judged as a new representative, and used to redefine both feature learning library and representative models over time; or 2) the new task with lower outlier probability will only refine the feature learning library. For model optimization, we cast this lifelong learning problem as an alternating direction minimization problem as a new task comes. Finally, we evaluate the proposed framework by analyzing several multi-task datasets, and the experimental results demonstrate that our FCL3 model can achieve better performance than most lifelong learning frameworks, even batch clustered multi-task learning models.
Flexible Deep Neural Network Processing The recent success of Deep Neural Networks (DNNs) has drastically improved the state of the art for many application domains. While achieving high accuracy performance, deploying state-of-the-art DNNs is a challenge since they typically require billions of expensive arithmetic computations. In addition, DNNs are typically deployed in ensemble to boost accuracy performance, which further exacerbates the system requirements. This computational overhead is an issue for many platforms, e.g. data centers and embedded systems, with tight latency and energy budgets. In this article, we introduce flexible DNNs ensemble processing technique, which achieves large reduction in average inference latency while incurring small to negligible accuracy drop. Our technique is flexible in that it allows for dynamic adaptation between quality of results (QoR) and execution runtime. We demonstrate the effectiveness of the technique on AlexNet and ResNet-50 using the ImageNet dataset. This technique can also easily handle other types of networks.
Flexible Parametric Model “Parametric Model”
Flexible Representative Democracy
We introduce Flexible Representative Democracy (FRD), a novel hybrid of Representative Democracy (RD) and Direct Democracy (DD), in which voters can alter the issue-dependent weights of a set of elected representatives. In line with the literature on Interactive Democracy, our model allows the voters to actively determine the degree to which the democracy is direct versus representative. However, unlike Liquid Democracy, FRD uses strictly non-transitive delegations, making delegation cycles impossible, and maintains a fixed set of accountable elected representatives. We present FRD and analyze it using a computational approach with issues that are binary and symmetric; we compare the outcomes of various democratic systems using Direct Democracy with majority voting as an ideal baseline. First, we demonstrate the shortcomings of Representative Democracy. We provide NP-Hardness results for electing an ideal set of representatives, discuss pathologies, and demonstrate empirically that common polynomial-time multi-winner election rules for selecting representatives do not perform well in expectation. To analyze the behavior of FRD, we begin by providing theoretical results on how issue-specific delegations determine outcomes. Finally, we provide empirical results comparing the outcomes of RD with fixed sets of proxies across issues versus FRD with issue-specific delegations. Our results show that variants of Proxy Voting yield no discernible benefit over RD and reveal the potential for FRD to improve outcomes as voter participation increases, further motivating the use of issue-specific delegations.
Flexible Unsupervised Neural Network
Deep neural networks have demonstrated high accuracy in image classification tasks. However, they were shown to be weak against adversarial examples: a small perturbation in the image which changes the classification output dramatically. In recent years, several defenses have been proposed to solve this issue in supervised classification tasks. We propose a method to obtain robust features in unsupervised learning tasks against adversarial attacks. Our method differs from existing solutions by directly learning the robust features without the need to project the adversarial examples in the original examples distribution space. A first auto-encoder A1 is in charge of perturbing the input image to fool another auto-encoder A2 which is in charge of regenerating the original image. A1 tries to find the less perturbed image under the constraint that the error in the output of A2 should be at least equal to a threshold. Thanks to this training, the encoder of A2 will be robust against adversarial attacks and could be used in different tasks like classification. Using state-of-art network architectures, we demonstrate the robustness of the features obtained thanks to this method in classification tasks.
FlexNGIA From virtual reality and telepresence, to augmented reality, holoportation, and remotely controlled robotics, these future network applications promise an unprecedented development for society, economics and culture by revolutionizing the way we live, learn, work and play. In order to deploy such futuristic applications and to cater to their performance requirements, recent trends stressed the need for the Tactile Internet, an Internet that, according to the International Telecommunication Union, combines ultra low latency with extremely high availability, reliability and security. Unfortunately, today’s Internet falls short when it comes to providing such stringent requirements due to several fundamental limitations in the design of the current network architecture and communication protocols. This brings the need to rethink the network architecture and protocols, and efficiently harness recent technological advances in terms of virtualization and network softwarization to design the Tactile Internet of the future. In this paper, we start by analyzing the characteristics and requirements of future networking applications. We then highlight the limitations of the traditional network architecture and protocols and their inability to cater to these requirements. Afterward, we put forward a novel network architecture adapted to the Tactile Internet called FlexNGIA, a Flexible Next-Generation Internet Architecture. We then describe some use-cases where we discuss the potential mechanisms and control loops that could be offered by FlexNGIA in order to ensure the required performance and reliability guarantees for future applications. Finally, we identify the key research challenges to further develop FlexNGIA towards a full-fledged architecture for the future Tactile Internet.
Flexpoint Deep neural networks are commonly developed and trained in 32-bit floating point format. Significant gains in performance and energy efficiency could be realized by training and inference in numerical formats optimized for deep learning. Despite advances in limited precision inference in recent years, training of neural networks in low bit-width remains a challenging problem. Here we present the Flexpoint data format, aiming at a complete replacement of 32-bit floating point format training and inference, designed to support modern deep network topologies without modifications. Flexpoint tensors have a shared exponent that is dynamically adjusted to minimize overflows and maximize available dynamic range. We validate Flexpoint by training AlexNet, a deep residual network and a generative adversarial network, using a simulator implemented with the neon deep learning framework. We demonstrate that 16-bit Flexpoint closely matches 32-bit floating point in training all three models, without any need for tuning of model hyperparameters. Our results suggest Flexpoint as a promising numerical format for future hardware for training and inference.
Flint Serverless architectures organized around loosely-coupled function invocations represent an emerging design for many applications. Recent work mostly focuses on user-facing products and event-driven processing pipelines. In this paper, we explore a completely different part of the application space and examine the feasibility of analytical processing on big data using a serverless architecture. We present Flint, a prototype Spark execution engine that takes advantage of AWS Lambda to provide a pure pay-as-you-go cost model. With Flint, a developer uses PySpark exactly as before, but without needing an actual Spark cluster. We describe the design, implementation, and performance of Flint, along with the challenges associated with serverless analytics.
Flood Algorithm With the U-matrix Ultsch (Information and Classification: Concepts, Methods and Applications, pp. 307-313, Springer, 1993) introduced a powerful visual representation of the Self Organizing Maps results. We propose an approach that utilizes the U-matrix to identify outlying data points. Then the revised subsample (i.e. the initial sample minus the outlying points) is used to give a robust estimation of location and scatter.
Flotilla Flotilla is a human friendly service for task execution. It allows you to focus on the work you’re doing rather than how to do it. In other words, Flotilla takes the struggle out of defining and running containerized jobs.
Flow Conversational machine comprehension requires a deep understanding of the conversation history. To enable traditional, single-turn models to encode the history comprehensively, we introduce Flow, a mechanism that can incorporate intermediate representations generated during the process of answering previous questions, through an alternating parallel processing structure. Compared to shallow approaches that concatenate previous questions/answers as input, Flow integrates the latent semantics of the conversation history more deeply. Our model, FlowQA, shows superior performance on two recently proposed conversational challenges (+7.2% F1 on CoQA and +4.0% on QuAC). The effectiveness of Flow also shows in other tasks. By reducing sequential instruction understanding to conversational machine comprehension, FlowQA outperforms the best models on all three domains in SCONE, with +1.8% to +4.4% improvement in accuracy.
Flow Classification Algorithm
Flow Map Flow maps in cartography are a mix of maps and flow charts, that ‘show the movement of objects from one location to another, such as the number of people in a migration, the amount of goods being traded, or the number of packets in a network’.
Flow-Based Intrinsic Curiosity Module
Exploration bonuses derived from the novelty of observations in an environment have become a popular approach to motivate exploration for reinforcement learning (RL) agents in the past few years. Recent methods such as curiosity-driven exploration usually estimate the novelty of new observations by the prediction errors of their system dynamics models. In this paper, we introduce the concept of optical flow estimation from the field of computer vision to the RL domain and utilize the errors from optical flow estimation to evaluate the novelty of new observations. We introduce a flow-based intrinsic curiosity module (FICM) capable of learning the motion features and understanding the observations in a more comprehensive and efficient fashion. We evaluate our method and compare it with a number of baselines on several benchmark environments, including Atari games, Super Mario Bros., and ViZDoom. Our results show that the proposed method is superior to the baselines in certain environments, especially for those featuring sophisticated moving patterns or with high-dimensional observation spaces. We further analyze the hyper-parameters used in the training phase and discuss our insights into them.
FlowQA “Flow”
Flowr Flowr is a robust and scalable framework for designing and deploying computing pipelines in an easy-to-use fashion. It implements a scatter-gather approach using computing clusters, simplifying the concept to the use of five simple terms (in submission and dependency types). Most importantly, it is flexible, such that customizing existing pipelines is easy, and since it works across several computing environments (LSF, SGE, Torque, and SLURM), it is portable.
Floyd-Warshall Algorithm In computer science, the Floyd-Warshall algorithm is an algorithm for finding shortest paths in a weighted graph with positive or negative edge weights (but with no negative cycles).[1][2] A single execution of the algorithm will find the lengths (summed weights) of shortest paths between all pairs of vertices. Although it does not return details of the paths themselves, it is possible to reconstruct the paths with simple modifications to the algorithm. Versions of the algorithm can also be used for finding the transitive closure of a relation {\displaystyle R} R, or (in connection with the Schulze voting system) widest paths between all pairs of vertices in a weighted graph.
FluidNets We present FluidNets, an approach to automate the design of neural network structures. FluidNets iteratively shrinks and expands a network, shrinking via a resource-weighted sparsifying regularizer on activations and expanding via a uniform multiplicative factor on all layers. In contrast to previous approaches, our method is scalable to large networks, adaptable to specific resource constraints (e.g. the number of floating-point operations per inference), and capable of increasing the network’s performance. When applied to standard network architectures on a wide variety of datasets, our approach discovers novel structures in each domain, obtaining higher performance while respecting the resource constraint.
F-Measure In statistical analysis of binary classification, the F1 score (also F-score or F-measure) is a measure of a test’s accuracy. It considers both the precision p and the recall r of the test to compute the score: p is the number of correct positive results divided by the number of all positive results, and r is the number of correct positive results divided by the number of positive results that should have been returned. The F1 score can be interpreted as a weighted average of the precision and recall, where an F1 score reaches its best value at 1 and worst score at 0. The traditional F-measure or balanced F-score (F1 score) is the harmonic mean of precision and recall.
FML-kNN Efficient management and analysis of large volumes of data is a demanding task of increasing scientific and industrial importance, as the ubiquitous generation of information governs more and more aspects of human life. In this article, we introduce FML-kNN, a novel distributed processing framework for Big Data that performs probabilistic classification and regression, implemented in Apache Flink. The framework’s core is consisted of a k-nearest neighbor joins algorithm which, contrary to similar approaches, is executed in a single distributed session and is able to operate on very large volumes of data of variable granularity and dimensionality. We assess FML-kNN’s performance and scalability in a detailed experimental evaluation, in which it is compared to similar methods implemented in Apache Hadoop, Spark, and Flink distributed processing engines. The results indicate an overall superiority of our framework in all the performed comparisons. Further, we apply FML-kNN in two motivating uses cases for water demand management, against real-world domestic water consumption data. In particular, we focus on forecasting water consumption using 1-h smart meter data, and extracting consumer characteristics from water use data in the shower. We further discuss on the obtained results, demonstrating the framework’s potential in useful knowledge extraction.
FM-Pair In this work, we propose FM-Pair, an adaptation of Factorization Machines with a pairwise loss function, making them effective for datasets with implicit feedback. The optimization model in FM-Pair is based on the BPR (Bayesian Personalized Ranking) criterion, which is a well-established pairwise optimization model. FM-Pair retains the advantages of FMs on generality, expressiveness and performance and yet it can be used for datasets with implicit feedback. We also propose how to apply FM-Pair effectively on two collaborative filtering problems, namely, context-aware recommendation and cross-domain collaborative filtering. By performing experiments on different datasets with explicit or implicit feedback we empirically show that in most of the tested datasets, FM-Pair beats state-of-the-art learning-to-rank methods such as BPR-MF (BPR with Matrix Factorization model). We also show that FM-Pair is significantly more effective for ranking, compared to the standard FMs model. Moreover, we show that FM-Pair can utilize context or cross-domain information effectively as the accuracy of recommendations would always improve with the right auxiliary features. Finally we show that FM-Pair has a linear time complexity and scales linearly by exploiting additional features.
FOCA Modeling an ontology is a hard and time-consuming task. Although methodologies are useful for ontologists to create good ontologies, they do not help with the task of evaluating the quality of the ontology to be reused. For these reasons, it is imperative to evaluate the quality of the ontology after constructing it or before reusing it. Few studies usually present only a set of criteria and questions, but no guidelines to evaluate the ontology. The effort to evaluate an ontology is very high as there is a huge dependence on the evaluator’s expertise to understand the criteria and questions in depth. Moreover, the evaluation is still very subjective. This study presents a novel methodology for ontology evaluation, taking into account three fundamental principles: i) it is based on the Goal, Question, Metric approach for empirical evaluation; ii) the goals of the methodologies are based on the roles of knowledge representations combined with specific evaluation criteria; iii) each ontology is evaluated according to the type of ontology. The methodology was empirically evaluated using different ontologists and ontologies of the same domain. The main contributions of this study are: i) defining a step-by-step approach to evaluate the quality of an ontology; ii) proposing an evaluation based on the roles of knowledge representations; iii) the explicit difference of the evaluation according to the type of the ontology iii) a questionnaire to evaluate the ontologies; iv) a statistical model that automatically calculates the quality of the ontologies.
FocusPixels This paper describes AutoFocus, an efficient multi-scale inference algorithm for deep-learning based object detectors. Instead of processing an entire image pyramid, AutoFocus adopts a coarse to fine approach and only processes regions which are likely to contain small objects at finer scales. This is achieved by predicting category agnostic segmentation maps for small objects at coarser scales, called FocusPixels. FocusPixels can be predicted with high recall, and in many cases, they only cover a small fraction of the entire image. To make efficient use of FocusPixels, an algorithm is proposed which generates compact rectangular FocusChips which enclose FocusPixels. The detector is only applied inside FocusChips, which reduces computation while processing finer scales. Different types of error can arise when detections from FocusChips of multiple scales are combined, hence techniques to correct them are proposed. AutoFocus obtains an mAP of 47.9% (68.3% at 50% overlap) on the COCO test-dev set while processing 6.4 images per second on a Titan X (Pascal) GPU. This is 2.5X faster than our multi-scale baseline detector and matches its mAP. The number of pixels processed in the pyramid can be reduced by 5X with a 1% drop in mAP. AutoFocus obtains more than 10% mAP gain compared to RetinaNet but runs at the same speed with the same ResNet-101 backbone.
FOFE-Net “Fixed-Size Ordinally Forgetting Encoding”
FogBus The requirement of supporting both latency sensitive and computing intensive Internet of Things (IoT) applications is consistently boosting the necessity for integrating Edge, Fog and Cloud infrastructure. Although there are a number of real-world frameworks attempt to support such integration, they have many limitations from various perspectives including platform independence, security, resource management and multi-application assistance. To address these limitations, we propose a simplified but effective framework, named FogBus for facilitating end-to-end IoT-Fog(Edge)-Cloud integration. FogBus offers a platform independent interface to IoT applications and computing instances for execution and interaction. It not only assists developers in building applications but also helps users in running multiple applications at a time and service providers to manage their resources. In addition, FogBus applies Blockchain, authentication and encryption techniques to secure operations on sensitive data. Because of its lightweight and cross platform software systems, it is easy to deploy, scalable and cost efficient. We demonstrate the effectiveness of our framework by creating a computing environment with it that integrates finger pulse oximeter as IoT devices with Smartphone-based gateway and Raspberry Pi-based Fog nodes for Sleep Apnea analysis. We also run several experiments on this computing environment varying FogBus settings. The experimental results show that different FogBus settings can improve latency, energy, network and CPU usage of the computing infrastructure.
FogLearn Big data analytics with the cloud computing are one of the emerging area for processing and analytics. Fog computing is the paradigm where fog devices help to reduce latency and increase throughput for assisting at the edge of the client. This paper discussed the emergence of fog computing for mining analytics in big data from geospatial and medical health applications. This paper proposed and developed fog computing based framework i.e. FogLearn for application of K-means clustering in Ganga River Basin Management and real world feature data for detecting diabetes patients suffering from diabetes mellitus. Proposed architecture employed machine learning on deep learning framework for analysis of pathological feature data that obtained from smart watches worn by the patients with diabetes and geographical parameters of River Ganga basin geospatial database. The results showed that fog computing hold an immense promise for analysis of medical and geospatial big data.
Folium Python Data. Leaflet.js Maps. Folium builds on the data wrangling strengths of the Python ecosystem and the mapping strengths of the Leaflet.js library. Manipulate your data in Python, then visualize it in on a Leaflet map via Folium. Concept: Folium makes it easy to visualize data that’s been manipulated in Python on an interactive Leaflet map. It enables both the binding of data to a map for choropleth visualizations as well as passing Vincent/Vega visualizations as markers on the map. The library has a number of built-in tilesets from OpenStreetMap, MapQuest Open, MapQuest Open Aerial, Mapbox, and Stamen, and supports custom tilesets with Mapbox or Cloudmade API keys. Folium supports both GeoJSON and TopoJSON overlays, as well as the binding of data to those overlays to create choropleth maps with color-brewer color schemes.
Creating interactive crime maps with Folium
Folksodriven The Folksodriven framework makes it possible for data scientists to define an ontology environment where searching for buried patterns that have some kind of predictive power to build predictive models more effectively. It accomplishes this through an abstractions that isolate parameters of the predictive modeling process searching for patterns and designing the feature set, too. To reflect the evolving knowledge, this paper considers ontologies based on folksonomies according to a new concept structure called ‘Folksodriven’ to represent folksonomies. So, the studies on the transformational regulation of the Folksodriven tags are regarded to be important for adaptive folksonomies classifications in an evolving environment used by Intelligent Systems to represent the knowledge sharing. Folksodriven tags are used to categorize salient data points so they can be fed to a machine-learning system and ‘featurizing’ the data.
In this paper we present the FolksoDriven Cloud (FDC) built on Cloud and on Semantic technologies. Cloud computing has emerged in these recent years as the new paradigm for the provision of on-demand distributed computing resources. Semantic Web can be used for relationship between different data and descriptions of services to annotate provenance of repositories on ontologies. The FDC service is composed of a back-end which submits and monitors the documents, and a user front-end which allows users to schedule on-demand operations and to watch the progress of running processes. The impact of the proposed method is illustrated on a user since its inception.
Folksonomy A folksonomy is a system in which users apply public tags to online items, typically to aid them in re-finding those items. This can give rise to a classification system based on those tags and their frequencies, in contrast to a taxonomic classification specified by the owners of the content when it is published. This practice is also known as collaborative tagging, social classification, social indexing, and social tagging. However, these terms have slightly different meanings than folksonomy. Folksonomy was originally the result of personal free tagging of information for ones own retrieval. Social tagging is the application of tags in an open online environment where the tags of other users are available to others. Collaborative tagging (also known as group tagging) is tagging performed by a group of users. This type of folksonomy is commonly used in cooperative and collaborative projects such as research, content repositories, and social bookmarking. The term was coined by Thomas Vander Wal in 2004 as a portmanteau of folk and taxonomy. Folksonomies became popular as part of social software applications such as social bookmarking and photograph annotation that enable users to collectively classify and find information via shared tags. Some websites include tag clouds as a way to visualize tags in a folksonomy. Folksonomies can be used for K-12 education, business, and higher education. More specifically, folksonomies may be implemented for social bookmarking, teacher resource repositories, e-learning systems, collaborative learning, collaborative research, and professional development.
Follow The (Proximally) Regularized Leader
Predicting ad click-through rates (CTR) is a massive-scale learning problem that is central to the multi-billion dollar online advertising industry. We present a selection of case studies and topics drawn from recent experiments in the setting of a deployed CTR prediction system. These include improvements in the context of traditional supervised learning based on an FTRL-Proximal online learning algorithm (which has excellent sparsity and convergence properties) and the use of per-coordinate learning rates. We also explore some of the challenges that arise in a real-world system that may appear at first to be outside the domain of traditional machine learning research. These include useful tricks for memory savings, methods for assessing and visualizing performance, practical methods for providing confidence estimates for predicted probabilities, calibration methods, and methods for automated management of features. Finally, we also detail several directions that did not turn out to be beneficial for us, despite promising results elsewhere in the literature. The goal of this paper is to highlight the close relationship between theoretical advances and practical engineering in this industrial setting, and to show the depth of challenges that appear when applying traditional machine learning methods in a complex dynamic system.
Follow the Leader
A natural algorithm to use in the OCO framework is Follow the Leader, which tries to minimize the regret over all of the previous time steps.
Follow the Regularized Leader
To avoid the failure of FTL we can try to “regularize” the weight vectors by adding a penalty function R(w) to the objective. This yields the FoReL algorithm.
Force Directed Graph Force-directed graph drawing algorithms are a class of algorithms for drawing graphs in an aesthetically pleasing way. Their purpose is to position the nodes of a graph in two-dimensional or three-dimensional space so that all the edges are of more or less equal length and there are as few crossing edges as possible, by assigning forces among the set of edges and the set of nodes, based on their relative positions, and then using these forces either to simulate the motion of the edges and nodes or to minimize their energy. While graph drawing can be a difficult problem, force-directed algorithms, being physical simulations, usually require no special knowledge about graph theory such as planarity.
Force Layout
Force-Directed Graph
FORECAST-CLSTM With the highly demand of large-scale and real-time weather service for public, a refinement of short-time cloudage prediction has become an essential part of the weather forecast productions. To provide a weather-service-compliant cloudage nowcasting, in this paper, we propose a novel hierarchical Convolutional Long-Short-Term Memory network based deep learning model, which we term as FORECAST-CLSTM, with a new Forecaster loss function to predict the future satellite cloud images. The model is designed to fuse multi-scale features in the hierarchical network structure to predict the pixel value and the morphological movement of the cloudage simultaneously. We also collect about 40K infrared satellite nephograms and create a large-scale Satellite Cloudage Map Dataset(SCMD). The proposed FORECAST-CLSTM model is shown to achieve better prediction performance compared with the state-of-the-art ConvLSTM model and the proposed Forecaster Loss Function is also demonstrated to retain the uncertainty of the real atmosphere condition better than conventional loss function.
ForensicTransfer Distinguishing fakes from real images is becoming increasingly difficult as new sophisticated image manipulation approaches come out by the day. Convolutional neural networks (CNN) show excellent performance in detecting image manipulations when they are trained on a specific forgery method. However, on examples from unseen manipulation approaches, their performance drops significantly. To address this limitation in transferability, we introduce ForensicTransfer. ForensicTransfer tackles two challenges in multimedia forensics. First, we devise a learning-based forensic detector which adapts well to new domains, i.e., novel manipulation methods. Second we handle scenarios where only a handful of fake examples are available during training. To this end, we learn a forensic embedding that can be used to distinguish between real and fake imagery. We are using a new autoencoder-based architecture which enforces activations in different parts of a latent vector for the real and fake classes. Together with the constraint of correct reconstruction this ensures that the latent space keeps all the relevant information about the nature of the image. Therefore, the learned embedding acts as a form of anomaly detector; namely, an image manipulated from an unseen method will be detected as fake provided it maps sufficiently far away from the cluster of real images. Comparing with prior works, ForensicTransfer shows significant improvements in transferability, which we demonstrate in a series of experiments on cutting-edge benchmarks. For instance, on unseen examples, we achieve up to 80-85% in terms of accuracy compared to 50-59%, and with only a handful of seen examples, our performance already reaches around 95%.
FORest Graph-Embedded deep feedforward NETwork
A unique challenge in predictive model building for omics data has been the small number of samples $(n)$ versus the large amount of features $(p)$. This ‘$n\ll p$’ property brings difficulties for disease outcome classification using deep learning techniques. Sparse learning by incorporating external gene network information such as the graph-embedded deep feedforward network (GEDFN) model has been a solution to this issue. However, such methods require an existing feature graph, and potential mis-specification of the feature graph can be harmful on classification and feature selection. To address this limitation and develop a robust classification model without relying on external knowledge, we propose a \underline{for}est \underline{g}raph-\underline{e}mbedded deep feedforward \underline{net}work (forgeNet) model, to integrate the GEDFN architecture with a forest feature graph extractor, so that the feature graph can be learned in a supervised manner and specifically constructed for a given prediction task. To validate the method’s capability, we experimented the forgeNet model with both synthetic and real datasets. The resulting high classification accuracy suggests that the method is a valuable addition to sparse deep learning models for omics data.
Forest Packing Machine learning has an emerging critical role in high-performance computing to modulate simulations, extract knowledge from massive data, and replace numerical models with efficient approximations. Decision forests are a critical tool because they provide insight into model operation that is critical to interpreting learned results. While decision forests are trivially parallelizable, the traversals of tree data structures incur many random memory accesses and are very slow. We present memory packing techniques that reorganize learned forests to minimize cache misses during classification. The resulting layout is hierarchical. At low levels, we pack the nodes of multiple trees into contiguous memory blocks so that each memory access fetches data for multiple trees. At higher levels, we use leaf cardinality to identify the most popular paths through a tree and collocate those paths in cache lines. We extend this layout with out-of-order execution and cache-line prefetching to increase memory throughput. Together, these optimizations increase the performance of classification in ensembles by a factor of four over an optimized C++ implementation and a actor of 50 over a popular R language implementation.
ForGAN Time series forecasting is one of the challenging problems for humankind. Traditional forecasting methods using mean regression models have severe shortcomings in reflecting real-world fluctuations. While new probabilistic methods rush to rescue, they fight with technical difficulties like quantile crossing or selecting a prior distribution. To meld the different strengths of these fields while avoiding their weaknesses as well as to push the boundary of the state-of-the-art, we introduce ForGAN – one step ahead probabilistic forecasting with generative adversarial networks. ForGAN utilizes the power of the conditional generative adversarial network to learn the data generating distribution and compute probabilistic forecasts from it. We argue how to evaluate ForGAN in opposition to regression methods. To investigate probabilistic forecasting of ForGAN, we create a new dataset and demonstrate our method abilities on it. This dataset will be made publicly available for comparison. Furthermore, we test ForGAN on two publicly available datasets, namely Mackey-Glass dataset and Internet traffic dataset (A5M) where the impressive performance of ForGAN demonstrate its high capability in forecasting future values.
Forgiver-First Aggregation
This work addresses a new problem of learning generative adversarial networks (GANs) from multiple data collections that are each i) owned separately and privately by different clients and ii) drawn from a non-identical distribution that comprises different classes. Given such multi-client and non-iid data as input, we aim to achieve a distribution involving all the classes input data can belong to, while keeping the data decentralized and private in each client storage. Our key contribution to this end is a new decentralized approach for learning GANs from non-iid data called Forgiver-First Update (F2U), which a) asks clients to train an individual discriminator with their own data and b) updates a generator to fool the most `forgiving’ discriminators who deem generated samples as the most real. Our theoretical analysis proves that this updating strategy indeed allows the decentralized GAN to learn a generator’s distribution with all the input classes as its global optimum based on f-divergence minimization. Moreover, we propose a relaxed version of F2U called Forgiver-First Aggregation (F2A), which adaptively aggregates the discriminators while emphasizing forgiving ones to perform well in practice. Our empirical evaluations with image generation tasks demonstrated the effectiveness of our approach over state-of-the-art decentralized learning methods.
Forgiver-First Update
This work addresses a new problem of learning generative adversarial networks (GANs) from multiple data collections that are each i) owned separately and privately by different clients and ii) drawn from a non-identical distribution that comprises different classes. Given such multi-client and non-iid data as input, we aim to achieve a distribution involving all the classes input data can belong to, while keeping the data decentralized and private in each client storage. Our key contribution to this end is a new decentralized approach for learning GANs from non-iid data called Forgiver-First Update (F2U), which a) asks clients to train an individual discriminator with their own data and b) updates a generator to fool the most `forgiving’ discriminators who deem generated samples as the most real. Our theoretical analysis proves that this updating strategy indeed allows the decentralized GAN to learn a generator’s distribution with all the input classes as its global optimum based on f-divergence minimization. Moreover, we propose a relaxed version of F2U called Forgiver-First Aggregation (F2A), which adaptively aggregates the discriminators while emphasizing forgiving ones to perform well in practice. Our empirical evaluations with image generation tasks demonstrated the effectiveness of our approach over state-of-the-art decentralized learning methods.
Formal Concept Analysis
In information science, formal concept analysis is a principled way of deriving a concept hierarchy or formal ontology from a collection of objects and their properties. Each concept in the hierarchy represents the set of objects sharing the same values for a certain set of properties; and each sub-concept in the hierarchy contains a subset of the objects in the concepts above it. The term was introduced by Rudolf Wille in 1984, and builds on applied lattice and order theory that was developed by Garrett Birkhoff and others in the 1930s. Formal concept analysis finds practical application in fields including data mining, text mining, machine learning, knowledge management, semantic web, software development, chemistry and biology.
Formula Evolution Map
“Mathematics Content Understanding”
Fortified Network Deep networks have achieved impressive results across a variety of important tasks. However a known weakness is a failure to perform well when evaluated on data which differ from the training distribution, even if these differences are very small, as is the case with adversarial examples. We propose Fortified Networks, a simple transformation of existing networks, which fortifies the hidden layers in a deep network by identifying when the hidden states are off of the data manifold, and maps these hidden states back to parts of the data manifold where the network performs well. Our principal contribution is to show that fortifying these hidden states improves the robustness of deep networks and our experiments (i) demonstrate improved robustness to standard adversarial attacks in both black-box and white-box threat models; (ii) suggest that our improvements are not primarily due to the gradient masking problem and (iii) show the advantage of doing this fortification in the hidden layers instead of the input space.
Forward Projection Dimensionality reduction is a common method for analyzing and visualizing high-dimensional data. However, reasoning dynamically about the results of a dimensionality reduction is difficult. Dimensionality-reduction algorithms use complex optimizations to reduce the number of dimensions of a dataset, but these new dimensions often lack a clear relation to the initial data dimensions, thus making them difficult to interpret. Here we propose a visual interaction framework to improve dimensionality-reduction based exploratory data analysis. We introduce two interaction techniques, forward projection and backward projection, for dynamically reasoning about dimensionally reduced data. We also contribute two visualization techniques, prolines and feasibility maps, to facilitate the effective use of the proposed interactions. We apply our framework to PCA and autoencoder-based dimensionality reductions. Through data-exploration examples, we demonstrate how our visual interactions can improve the use of dimensionality reduction in exploratory data analysis.
Forward Search The Forward Search is a powerful general method, incorporating flexible data-driven trimming, for the detection of outliers and unsuspected structure in data and so for building robust models. Starting from small subsets of data, observations that are close to the fitted model are added to the observations used in parameter estimation. As this subset grows we monitor parameter estimates, test statistics and measures of fit such as residuals.
Forward Slice We propose a method for stochastic optimization: ‘Forward Slice’. We evaluate its performance and apply to design problems in Section 3. At its core, our method is based on the procedure that Neal (2003) called the `slice sampling’ procedure , which was originally developed as a Markov chain Monte Carlo sampling procedure to draw samples from a target distribution. The slice sampling method relies on an auxiliary variable which de nes a level at which we slice the target density to obtain regions from which we draw samples of the target distribution. Similar to Neal’s method, our procedure uses an auxiliary variable for stochastic optimization that also de nes the slices, but of an objective function to be maximized (or minimized). Moreover, unlike with Neal’s method, the auxiliary variable in our approach is not sampled and takes on non-decreasing values in the sequential iterations of the procedure so that, for a given pre{speci ed tolerance, at the end of the procedure we attain the maxima and the argument of the maxima (or close values given the selected tolerance level).
Forward Thinking We present a general framework for training deep neural networks without backpropagation. This substantially decreases training time and also allows for construction of deep networks with many sorts of learners, including networks whose layers are defined by functions that are not easily differentiated, like decision trees. The main idea is that layers can be trained one at a time, and once they are trained, the input data are mapped forward through the layer to create a new learning problem. The process is repeated, transforming the data through multiple layers, one at a time, rendering a new data set, which is expected to be better behaved, and on which a final output layer can achieve good performance. We call this forward thinking and demonstrate a proof of concept by achieving state-of-the-art accuracy on the MNIST dataset for convolutional neural networks. We also provide a general mathematical formulation of forward thinking that allows for other types of deep learning problems to be considered.
Forward Thinking Deep Random Forest The success of deep neural networks has inspired many to wonder whether other learners could benefit from deep, layered architectures. We present a general framework called forward thinking for deep learning that generalizes the architectural flexibility and sophistication of deep neural networks while also allowing for (i) different types of learning functions in the network, other than neurons, and (ii) the ability to adaptively deepen the network as needed to improve results. This is done by training one layer at a time, and once a layer is trained, the input data are mapped forward through the layer to create a new learning problem. The process is then repeated, transforming the data through multiple layers, one at a time, rendering a new dataset, which is expected to be better behaved, and on which a final output layer can achieve good performance. In the case where the neurons of deep neural nets are replaced with decision trees, we call the result a Forward Thinking Deep Random Forest (FTDRF). We demonstrate a proof of concept by applying FTDRF on the MNIST dataset. We also provide a general mathematical formulation that allows for other types of deep learning problems to be considered.
FoveaBox We present FoveaBox, an accurate, flexible and completely anchor-free framework for object detection. While almost all state-of-the-art object detectors utilize the predefined anchors to enumerate possible locations, scales and aspect ratios for the search of the objects, their performance and generalization ability are also limited to the design of anchors. Instead, FoveaBox directly learns the object existing possibility and the bounding box coordinates without anchor reference. This is achieved by: (a) predicting category-sensitive semantic maps for the object existing possibility, and (b) producing category-agnostic bounding box for each position that potentially contains an object. The scales of target boxes are naturally associated with feature pyramid representations for each input image. Without bells and whistles, FoveaBox achieves state-of-the-art single model performance of 42.1 AP on the standard COCO detection benchmark. Specially for the objects with arbitrary aspect ratios, FoveaBox brings in significant improvement compared to the anchor-based detectors. More surprisingly, when it is challenged by the stretched testing images, FoveaBox shows great robustness and generalization ability to the changed distribution of bounding box shapes. The code will be made publicly available.
FPDeep Deep Neural Networks (DNNs) have revolutionized numerous applications, but the demand for ever more performance remains unabated. Scaling DNN computations to larger clusters is generally done by distributing tasks in batch mode using methods such as distributed synchronous SGD. Among the issues with this approach is that to make the distributed cluster work with high utilization, the workload distributed to each node must be large, which implies nontrivial growth in the SGD mini-batch size. In this paper, we propose a framework called FPDeep, which uses a hybrid of model and layer parallelism to configure distributed reconfigurable clusters to train DNNs. This approach has numerous benefits. First, the design does not suffer from batch size growth. Second, novel workload and weight partitioning leads to balanced loads of both among nodes. And third, the entire system is a fine-grained pipeline. This leads to high parallelism and utilization and also minimizes the time features need to be cached while waiting for back-propagation. As a result, storage demand is reduced to the point where only on-chip memory is used for the convolution layers. We evaluate FPDeep with the Alexnet, VGG-16, and VGG-19 benchmarks. Experimental results show that FPDeep has good scalability to a large number of FPGAs, with the limiting factor being the FPGA-to-FPGA bandwidth. With 6 transceivers per FPGA, FPDeep shows linearity up to 83 FPGAs. Energy efficiency is evaluated with respect to GOPs/J. FPDeep provides, on average, 6.36x higher energy efficiency than comparable GPU servers.
fpgaConvNet In recent years, Convolutional Neural Networks (ConvNets) have become an enabling technology for a wide range of novel embedded Artificial Intelligence systems. Across the range of applications, the performance needs vary significantly, from high-throughput video surveillance to the very low-latency requirements of autonomous cars. In this context, FPGAs can provide a potential platform that can be optimally configured based on the different performance needs. However, the complexity of ConvNet models keeps increasing making their mapping to an FPGA device a challenging task. This work presents fpgaConvNet, an end-to-end framework for mapping ConvNets on FPGAs. The proposed framework employs an automated design methodology based on the Synchronous Dataflow (SDF) paradigm and defines a set of SDF transformations in order to efficiently explore the architectural design space. By selectively optimising for throughput, latency or multiobjective criteria, the presented tool is able to efficiently explore the design space and generate hardware designs from high-level ConvNet specifications, explicitly optimised for the performance metric of interest. Overall, our framework yields designs that improve the performance by up to 6.65x over highly optimised embedded GPU designs for the same power constraints in embedded environments.
FP-Growth Algorithm In Data Mining the task of finding frequent pattern in large databases is very important and has been studied in large scale in the past few years. Unfortunately, this task is computationally expensive, especially when a large number of patterns exist. The FP-Growth Algorithm, proposed by Han in , is an efficient and scalable method for mining the complete set of frequent patterns by pattern fragment growth, using an extended prefix-tree structure for storing compressed and crucial information about frequent patterns named frequent-pattern tree (FP-tree). In his study, Han proved that his method outperforms other popular methods for mining frequent patterns, e.g. the Apriori Algorithm and the TreeProjection. In some later works it was proved that FP-Growth has better performance than other methods, including Eclat and Relim. The popularity and efficiency of FP-Growth Algorithm contributes with many studies that propose variations to improve his performance.
FPV-TPV We explore the problem of intersection classification using monocular on-board passive vision, with the goal of classifying traffic scenes with respect to road topology. We divide the existing approaches into two broad categories according to the type of input data: (a) first person vision (FPV) approaches, which use an egocentric view sequence as the intersection is passed; and (b) third person vision (TPV) approaches, which use a single view immediately before entering the intersection. The FPV and TPV approaches each have advantages and disadvantages. Therefore, we aim to combine them into a unified deep learning framework. Experimental results show that the proposed FPV-TPV scheme outperforms previous methods and only requires minimal FPV/TPV measurements.
Fractal AI Fractal AI is a theory for general artificial intelligence. It allows to derive new mathematical tools that constitute the foundations for a new kind of stochastic calculus, by modelling information using cellular automaton-like structures instead of smooth functions. In the repository included we are presenting a new Agent, derived from the first principles of the theory, which is capable of solving Atari games several orders of magnitude more efficiently than other similar techniques, like Monte Carlo Tree Search. The code provided shows how it is now possible to beat some of the current state of the art benchmarks on Atari games, without previous learning and using less than 1000 samples to calculate each one of the actions when standard MCTS uses 3 Million samples. Among other things, Fractal AI makes it possible to generate a huge database of top performing examples with very little amount of computation required, transforming Reinforcement Learning into a supervised problem. The algorithm presented is capable of solving the exploration vs exploitation dilemma on both the discrete and continuous cases, while maintaining control over any aspect of the behavior of the Agent. From a general approach, new techniques presented here have direct applications to other areas such as: Non-equilibrium thermodynamics, chemistry, quantum physics, economics, information theory, and non-linear control theory.
Fractional Imputation
Fractional Langevin Monte Carlo
Along with the recent advances in scalable Markov Chain Monte Carlo methods, sampling techniques that are based on Langevin diffusions have started receiving increasing attention. These so called Langevin Monte Carlo (LMC) methods are based on diffusions driven by a Brownian motion, which gives rise to Gaussian proposal distributions in the resulting algorithms. Even though these approaches have proven successful in many applications, their performance can be limited by the light-tailed nature of the Gaussian proposals. In this study, we extend classical LMC and develop a novel Fractional LMC (FLMC) framework that is based on a family of heavy-tailed distributions, called $\alpha$-stable L\'{e}vy distributions. As opposed to classical approaches, the proposed approach can possess large jumps while targeting the correct distribution, which would be beneficial for efficient exploration of the state space. We develop novel computational methods that can scale up to large-scale problems and we provide formal convergence analysis of the proposed scheme. Our experiments support our theory: FLMC can provide superior performance in multi-modal settings, improved convergence rates, and robustness to algorithm parameters.
Frailty Model Frailty models are extensions of the proportional hazards model which is best known as the Cox model (Cox, 1972), the most popular model in survival analysis. Normally, in most clinical applications, survival analysis implicitly assumes a homogenous population to be studied. This means that all individuals sampled into that study are subject in principle under the same risk (e.g., risk of death, risk of disease recurrence). In many applications, the study population can not be assumed to be homogeneous but must be considered as a heterogeneous sample, i.e. a mixture of individuals with different hazards. For example, in many cases it is impossible to measure all relevant covariates related to the disease of interest, sometimes because of economical reasons, sometimes the importance of some covariates is still unknown. The frailty approach is a statistical modelling concept which aims to account for heterogeneity, caused by unmeasured covariates. In statistical terms, a frailty model is a random effect model for time-to-event data, where the random effect (the frailty) has a multiplicative effect on the baseline hazard function.
Frame Semantic Structure Extraction Debugging Frame Semantic Role Labeling
FrameNet In this work, we introduce the novel problem of identifying dense canonical 3D coordinate frames from a single RGB image. We observe that each pixel in an image corresponds to a surface in the underlying 3D geometry, where a canonical frame can be identified as represented by three orthogonal axes, one along its normal direction and two in its tangent plane. We propose an algorithm to predict these axes from RGB. Our first insight is that canonical frames computed automatically with recently introduced direction field synthesis methods can provide training data for the task. Our second insight is that networks designed for surface normal prediction provide better results when trained jointly to predict canonical frames, and even better when trained to also predict 2D projections of canonical frames. We conjecture this is because projections of canonical tangent directions often align with local gradients in images, and because those directions are tightly linked to 3D canonical frames through projective geometry and orthogonality constraints. In our experiments, we find that our method predicts 3D canonical frames that can be used in applications ranging from surface normal estimation, feature matching, and augmented reality.
FrameRank Video summarization has been extensively studied in the past decades. However, user-generated video summarization is much less explored since there lack large-scale video datasets within which human-generated video summaries are unambiguously defined and annotated. Toward this end, we propose a user-generated video summarization dataset – UGSum52 – that consists of 52 videos (207 minutes). In constructing the dataset, because of the subjectivity of user-generated video summarization, we manually annotate 25 summaries for each video, which are in total 1300 summaries. To the best of our knowledge, it is currently the largest dataset for user-generated video summarization. Based on this dataset, we present FrameRank, an unsupervised video summarization method that employs a frame-to-frame level affinity graph to identify coherent and informative frames to summarize a video. We use the Kullback-Leibler(KL)-divergence-based graph to rank temporal segments according to the amount of semantic information contained in their frames. We illustrate the effectiveness of our method by applying it to three datasets SumMe, TVSum and UGSum52 and show it achieves state-of-the-art results.
Francy Data visualization and interaction with large data sets is known to be essential and critical in many businesses today, and the same applies to research and teaching, in this case, when exploring large and complex mathematical objects. GAP is a computer algebra system for computational discrete algebra with an emphasis on computational group theory. The existing XGAP package for GAP works exclusively on the X Window System. It lacks abstraction between its mathematical and graphical cores, making it difficult to extend, maintain, or port. In this paper, we present Francy, a graphical semantics package for GAP. Francy is responsible for creating a representational structure that can be rendered using many GUI frameworks independent from any particular programming language or operating system. Building on this, we use state of the art web technologies that take advantage of an improved REPL environment, which is currently under development for GAP. The integration of this project with Jupyter provides a rich graphical environment full of features enhancing the usability and accessibility of GAP.
Frank-Wolfe Sparse Representation
In this paper, we consider the problem of selecting representatives from a data set for arbitrary supervised/unsupervised learning tasks. We identify a subset $S$ of a data set $A$ such that 1) the size of $S$ is much smaller than $A$ and 2) $S$ efficiently describes the entire data set, in a way formalized via auto-regression. The set $S$, also known as the exemplars of the data set $A$, is constructed by solving a convex auto-regressive version of dictionary learning where the dictionary and measurements are given by the data matrix. We show that in order to generate $|S| = k$ exemplars, our algorithm, Frank-Wolfe Sparse Representation (FWSR), only requires $\approx k$ iterations with a per-iteration cost that is quadratic in the size of $A$, an order of magnitude faster than state of the art methods. We test our algorithm against current methods on 4 different data sets and are able to outperform other exemplar finding methods in almost all scenarios. We also test our algorithm qualitatively by selecting exemplars from a corpus of Donald Trump and Hillary Clinton’s twitter posts.
Frank-Wolfe Type Boosting Algorithm
Boosting is a generic learning method for classification and regression. Yet, as the number of base hypotheses becomes larger, boosting can lead to a deterioration of test performance. Overfitting is an important and ubiquitous phenomenon, especially in regression settings. To avoid overfitting, we consider using $l_1$ regularization. We propose a novel Frank-Wolfe type boosting algorithm (FWBoost) applied to general loss functions. By using exponential loss, the FWBoost algorithm can be rewritten as a variant of AdaBoost for binary classification. FWBoost algorithms have exactly the same form as existing boosting methods, in terms of making calls to a base learning algorithm with different weights update. This direct connection between boosting and Frank-Wolfe yields a new algorithm that is as practical as existing boosting methods but with new guarantees and rates of convergence. Experimental results show that the test performance of FWBoost is not degraded with larger rounds in boosting, which is consistent with the theoretical analysis.
Free Component Analysis
We describe a method for unmixing mixtures of freely independent random variables in a manner analogous to the independent component analysis (ICA) based method for unmixing independent random variables from their additive mixtures. Random matrices play the role of free random variables in this context so the method we develop, which we call Free component analysis (FCA), unmixes matrices from additive mixtures of matrices. We describe the theory, the various algorithms, and compare FCA to ICA. We show that FCA performs comparably to, and often better than, ICA in every application, such as image and speech unmixing, where ICA has been known to succeed. Our computational experiments suggest that not-so-random matrices, such as images and spectrograms of waveforms are (closer to being) freer ‘in the wild’ than we might have theoretically expected.
Free Probability Theory Free probability is a mathematical theory that studies non-commutative random variables. The ‘freeness’ or free independence property is the analogue of the classical notion of independence, and it is connected with free products. This theory was initiated by Dan Voiculescu around 1986 in order to attack the free group factors isomorphism problem, an important unsolved problem in the theory of operator algebras. Given a free group on some number of generators, we can consider the von Neumann algebra generated by the group algebra, which is a type II1 factor. The isomorphism problem asks whether these are isomorphic for different numbers of generators. It is not even known if any two free group factors are isomorphic. This is similar to Tarski’s free group problem, which asks whether two different non-abelian finitely generated free groups have the same elementary theory.
A Simple Introduction to Free Probability Theory and its Application to Random Matrices
Freedman’s Paradox In statistical analysis, Freedman’s paradox, named after David Freedman, describes a problem in model selection whereby predictor variables with no explanatory power can appear artificially important. Freedman demonstrated (through simulation and asymptotic calculation) that this is a common occurrence when the number of variables is similar to the number of data points. Recently, new information-theoretic estimators have been developed in an attempt to reduce this problem, in addition to the accompanying issue of model selection bias, whereby estimators of predictor variables that have a weak relationship with the response variable are biased.
Freedman’s Paradox
Freemium Freemium is a pricing strategy by which a product or service (typically a digital offering such as software, media, games or web services) is provided free of charge, but money (premium) is charged for proprietary features, functionality, or virtual goods. The word “freemium” is a portmanteau neologism combining the two aspects of the business model: “free” and “premium”.
Freestyle Multilingual Image Question Answering
Freestyle Multilingual Image Question Answering (FM-IQA) dataset to train and evaluate our mQA model. It contains over 120,000 images and 250,000 freestyle Chinese question-answer pairs and their English translations. The quality of the generated answers of our mQA model on this dataset are evaluated by human judges through a Turing Test.
Frequency Principle Previous studies have shown that deep neural networks (DNNs) with common settings often capture target functions from low to high frequency, which is called Frequency Principle (F-Principle). It has also been shown that F-Principle can provide an understanding to the often observed good generalization ability of DNNs.
FRequency-AGnostic word Embedding
Continuous word representation (aka word embedding) is a basic building block in many neural network-based models used in natural language processing tasks. Although it is widely accepted that words with similar semantics should be close to each other in the embedding space, we find that word embeddings learned in several tasks are biased towards word frequency: the embeddings of high-frequency and low-frequency words lie in different subregions of the embedding space, and the embedding of a rare word and a popular word can be far from each other even if they are semantically similar. This makes learned word embeddings ineffective, especially for rare words, and consequently limits the performance of these neural network models. In this paper, we develop a neat, simple yet effective way to learn \emph{FRequency-AGnostic word Embedding} (FRAGE) using adversarial training. We conducted comprehensive studies on ten datasets across four natural language processing tasks, including word similarity, language modeling, machine translation and text classification. Results show that with FRAGE, we achieve higher performance than the baselines in all tasks.
Frequency-Based Kernel Kalman Filter
One main challenge for the design of networks is that traffic load is not generally known in advance. This makes it hard to adequately devote resources such as to best prevent or mitigate bottlenecks. While several authors have shown how to predict traffic in a coarse grained manner by aggregating flows, fine grained prediction of traffic at the level of individual flows, including bursty traffic, is widely considered to be impossible. This paper shows, to the best of our knowledge, the first approach to fine grained per flow traffic prediction. In short, we introduce the Frequency-based Kernel Kalman Filter (FKKF), which predicts individual flows’ behavior based on measurements. Our FKKF relies on the well known Kalman Filter in combination with a kernel to support the prediction of non linear functions. Furthermore we change the operating space from time to frequency space. In this space, into which we transform the input data via a Short-Time Fourier Transform (STFT), the peak structures of flows can be predicted after gleaning their key characteristics, with a Principal Component Analysis (PCA), from past and ongoing flows that stem from the same socket-to-socket connection. We demonstrate the effectiveness of our approach on popular benchmark traces from a university data center. Our approach predicts traffic on average across 17 out of 20 groups of flows with an average prediction error of 6.43% around 0.49 (average) seconds in advance, whilst existing coarse grained approaches exhibit prediction errors of 77% at best.
Frequent Pattern Mining The problem of frequent pattern mining is that of finding relationships among the items in a database. The problem can be stated as follows. Given a database D with transactions T1 … TN, determine all patterns P that are present in at least a fraction s of the transactions. The fraction s is referred to as the minimum support. The parameter s can be expressed either as an absolute number, or as a fraction of the total number of transactions in the database. Each transaction Ti can be considered a sparse binary vector, or as a set of discrete values representing the identifiers of the binary attributes that are instantiated to the value of 1. The problem was originally proposed in the context of market basket data in order to find frequent groups of items that are bought together. Thus, in this scenario, each attribute corresponds to an item in a superstore, and the binary value represents whether or not it is present in the transaction. Because the problem was originally proposed, it has been applied to numerous other applications in the context of data mining,Web log mining, sequential pattern mining, and software bug analysis.
Frequent Sequence Mining
Frequentist Information Criterion
The failure of the information-based Akaike Information Criterion (AIC) in the context of singular models can be rectified by the definition of a Frequentist Information Criterion (FIC). FIC applies a frequentist approximation to the computation of the model complexity, which can be estimated analytically in many contexts. Like AIC, FIC can be understood as an unbiased estimator of the model predictive performance and is therefore identical to AIC for regular models in the large-observation-number limit . In the presence of unidentifiable parameters, the complexity exhibits a more general, non-AIC-like scaling. For instance, both BIC-like (logN ) and Hannan-Quinn-like (loglogN ) scaling with observation number N are observed. Unlike the Bayesian model selection approach, FIC is free from {\it ad hoc} prior probability distributions and appears to be widely applicable to model selection problems. Finally we demonstrate that FIC (information-based inference) is equivalent to frequentist inference for an important class of models.
Frequently Updated Timestamped Structured Data
The Internet, and hence IoT, contains potentially billions of Frequently Updated Timestamped Structured (FUTS) data sources, such as real-time traffic reports, air pollution detection, temperature monitoring, crops monitoring, etc. FUTS data sources contain states and updates of physical world things.
FRESH Massive datasets of curves, such as time series and trajectories, are continuously generated by mobile and sensing devices. A relevant operation on curves is similarity search: given a dataset $S$ of curves, construct a data structure that, for any query curve $q$, finds the curves in $S$ similar to $q$. Similarity search is a computational demanding task, in particular when a robust distance function is used, such as the continuous Fr\’echet distance. In this paper, we propose FRESH, a novel approximate solution to find similar curves under the continuous Fr\’echet distance. FRESH leverages on a locality sensitive hashing scheme for detecting candidate near neighbors of the query curve, and a subsequent pruning step based on a pipeline of curve simplifications. By relaxing the requirement of exact and deterministic solutions, FRESH reaches high performance and outperforms the state-of-the-art approaches. The experiments indeed show that, with a recall larger than 80% and precision 100%, we have at least a factor 10 improvement in performance over a baseline given by the best solutions developed for the ACM SIGSPATIAL 2017 challenge on the Fr\’echet distance. Furthermore, the improvement peaks up to two orders of magnitude, and even more, by relaxing the precision.
Friedman Test The Friedman test is a non-parametric statistical test developed by Milton Friedman. Similar to the parametric repeated measures ANOVA, it is used to detect differences in treatments across multiple test attempts. The procedure involves ranking each row (or block) together, then considering the values of ranks by columns. Applicable to complete block designs, it is thus a special case of the Durbin test.
Frienemy Indecision REgion Dynamic Ensemble Selection
Frozen Analytics Frozen analytics to create and prototype rule and scoring system, using cross-validation, training sets, sampling and algorithms like traditional machine learning algorithms.
Full Normalization
Batch Normalization (BN) has been used extensively in deep learning to achieve faster training process and better resulting models. However, whether BN works strongly depends on how the batches are constructed during training and it may not converge to a desired solution if the statistics on a batch are not close to the statistics over the whole dataset. In this paper, we try to understand BN from an optimization perspective by formulating the optimization problem which motivates BN. We show when BN works and when BN does not work by analyzing the optimization problem. We then propose a refinement of BN based on compositional optimization techniques called Full Normalization (FN) to alleviate the issues of BN when the batches are not constructed ideally. We provide convergence analysis for FN and empirically study its effectiveness to refine BN.
Full Reference Image Quality Assessment
While it is nearly effortless for humans to quickly assess the perceptual similarity between two images, the underlying processes are thought to be quite complex. Despite this, the most widely used perceptual metrics today, such as PSNR and SSIM, are simple, shallow functions, and fail to account for many nuances of human perception. Recently, the deep learning community has found that features of the VGG network trained on the ImageNet classification task has been remarkably useful as a training loss for image synthesis. But how perceptual are these so-called ‘perceptual losses’? What elements are critical for their success? To answer these questions, we introduce a new Full Reference Image Quality Assessment (FR-IQA) dataset of perceptual human judgments, orders of magnitude larger than previous datasets. We systematically evaluate deep features across different architectures and tasks and compare them with classic metrics. We find that deep features outperform all previous metrics by huge margins. More surprisingly, this result is not restricted to ImageNet-trained VGG features, but holds across different deep architectures and levels of supervision (supervised, self-supervised, or even unsupervised). Our results suggest that perceptual similarity is an emergent property shared across deep visual representations.
full-FORCE Trained recurrent networks are powerful tools for modeling dynamic neural computations. We present a target-based method for modifying the full connectivity matrix of a recurrent network to train it to perform tasks involving temporally complex input/output transformations. The method introduces a second network during training to provide suitable ‘target’ dynamics useful for performing the task. Because it exploits the full recurrent connectivity, the method produces networks that perform tasks with fewer neurons and greater noise robustness than traditional least-squares (FORCE) approaches. In addition, we show how introducing additional input signals into the target-generating network, which act as task hints, greatly extends the range of tasks that can be learned and provides control over the complexity and nature of the dynamics of the trained, task-performing network.
Full-Jacobian Non-linear functions such as neural networks can be locally approximated by affine planes. Recent works make use of input-Jacobians, which describe the normal to these planes. In this paper, we introduce full-Jacobians, which includes this normal along with an additional intercept term called the bias-Jacobians, that together completely describe local planes. For ReLU neural networks, bias-Jacobians correspond to sums of gradients of outputs w.r.t. intermediate layer activations. We first use these full-Jacobians for distillation by aligning gradients of their intermediate representations. Next, we regularize bias-Jacobians alone to improve generalization. Finally, we show that full-Jacobian maps can be viewed as saliency maps. Experimental results show improved distillation on small data-sets, improved generalization for neural network training, and sharper saliency maps.
Fully Attention Based Information Retriever
Recurrent neural networks are now the state-of-the-art in natural language processing because they can build rich contextual representations and process texts of arbitrary length. However, recent developments on attention mechanisms have equipped feedforward networks with similar capabilities, hence enabling faster computations due to the increase in the number of operations that can be parallelized. We explore this new type of architecture in the domain of question-answering and propose a novel approach that we call Fully Attention Based Information Retriever (FABIR). We show that FABIR achieves competitive results in the Stanford Question Answering Dataset (SQuAD) while having fewer parameters and being faster at both learning and inference than rival methods.
Fully Conditional Specification
In this method, an imputation model for each variable with missing values is specified. This method is an iterative MCMC procedure. In each iteration, it sequentially imputes missing values starting from the first variable with missing values.
Fully Connected and Convolutional Generative Adversarial Network
Generative Adversarial Networks (GANs) are a powerful class of generative models. Despite their successes, the most appropriate choice of a GAN network architecture is still not well understood. GAN models for image synthesis have adopted a deep convolutional network architecture, which eliminates or minimizes the use of fully connected and pooling layers in favor of convolution layers in the generator and discriminator of GANs. In this paper, we demonstrate that a convolution network architecture utilizing deep fully connected layers and pooling layers can be more effective than the traditional convolution-only architecture, and we propose FCC-GAN (Fully Connected and Convolutional Generative Adversarial Network), a fully connected and convolutional GAN architecture. Models based on our FCC-GAN architecture learn both faster than the conventional architecture and also generate higher quality of samples. We demonstrate the effectiveness and stability of our approach across four popular image datasets.
Fully Convolution Networks
Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, improve on the previous best result in semantic segmentation. Our key insight is to build ‘fully convolutional’ networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning. We define and detail the space of fully convolutional networks, explain their application to spatially dense prediction tasks, and draw connections to prior models. We adapt contemporary classification networks (AlexNet, the VGG net, and GoogLeNet) into fully convolutional networks and transfer their learned representations by fine-tuning to the segmentation task. We then define a skip architecture that combines semantic information from a deep, coarse layer with appearance information from a shallow, fine layer to produce accurate and detailed segmentations. Our fully convolutional network achieves improved segmentation of PASCAL VOC (30% relative improvement to 67.2% mean IU on 2012), NYUDv2, SIFT Flow, and PASCAL-Context, while inference takes one tenth of a second for a typical image.
Improving Fully Convolution Network for Semantic Segmentation
Fully Convolutional Network
“Fully Convolution Networks”
Fully Convolutional one-Stage Object Detector
We propose a fully convolutional one-stage object detector (FCOS) to solve object detection in a per-pixel prediction fashion, analogue to semantic segmentation. Almost all state-of-the-art object detectors such as RetinaNet, SSD, YOLOv3, and Faster R-CNN rely on pre-defined anchor boxes. In contrast, our proposed detector FCOS is anchor-box free, as well as proposal free. By eliminating the pre-defined set of anchor boxes, FCOS completely avoids the complicated computation related to anchor boxes such as calculating overlapping during training and significantly reduces the training memory footprint. More importantly, we also avoid all hyper-parameters related to anchor boxes, which are often very sensitive to the final detection performance. With the only post-processing non-maximum suppression (NMS), our detector FCOS outperforms previous anchor-based one-stage detectors with the advantage of being much simpler. For the first time, we demonstrate a much simpler and flexible detection framework achieving improved detection accuracy. We hope that the proposed FCOS framework can serve as a simple and strong alternative for many other instance-level tasks.
Fully Convolutional two-Stream Fusion Network
In this paper, we propose a novel fully convolutional two-stream fusion network (FCTSFN) for interactive image segmentation. The proposed network includes two sub-networks: a two-stream late fusion network (TSLFN) that predicts the foreground at a reduced resolution, and a multi-scale refining network (MSRN) that refines the foreground at full resolution. The TSLFN includes two distinct deep streams followed by a fusion network. The intuition is that, since user interactions are more direction information on foreground/background than the image itself, the two-stream structure of the TSLFN reduces the number of layers between the pure user interaction features and the network output, allowing the user interactions to have a more direct impact on the segmentation result. The MSRN fuses the features from different layers of TSLFN with different scales, in order to seek the local to global information on the foreground to refine the segmentation result at full resolution. We conduct comprehensive experiments on four benchmark datasets. The results show that the proposed network achieves competitive performance compared to current state-of-the-art interactive image segmentation methods.
Fully Hyperbolic Convolutional Neural Networks Convolutional Neural Networks (CNN) have recently seen tremendous success in various computer vision tasks. However, their application to problems with high dimensional input and output has been limited by two factors. First, in the training stage, it is necessary to store network activations for back propagation. Second, in the inference stage, a few copies of the image are typically stored to be concatenated to other network states deeper in the network. In these settings, the memory requirements associated with storing activations can exceed what is feasible with current hardware. For the problem of image classification, reversible architectures have been proposed that allow one to recalculate activations in the backwards pass instead of storing them, however, such networks do not perform well for problems such as segmentation. Furthermore, currently only block reversible networks have been possible because pooling operations are not reversible. Motivated by the propagation of signals over physical networks, that are governed by the hyperbolic Telegraph equation, in this work we introduce a fully conservative hyperbolic network for problems with high dimensional input and output. We introduce a coarsening operation that allows completely reversible CNNs by using the Discrete Wavelet Transform and its inverse to both coarsen and interpolate the network state and change the number of channels. This means that during training we do not need to store the activations from the forward pass, and can train arbitrarily deep or wide networks. Furthermore, our network has a much lower memory footprint for inference. We show that we are able to achieve results comparable to the state of the art in image classification, depth estimation, and semantic segmentation, with a much lower memory footprint.
Fully Implicit Online Learning
Regularized online learning is widely used in machine learning. In this paper we analyze a class of regularized online algorithm with both non-linearized losses and non-linearized regularizers, which we call fully implicit online learning (FIOL). It is shown that because of avoiding the error of linearization, an extra additive regret gain can be obtained for FIOL. Then we show that by exploring the structure of the loss and regularizer, each iteration of FIOL can be exactly solved with time comparable to its linearized version, even if no closed-form solution exists. Experiments validate the proposed approaches.
Fully Learnable Group Convolution Module
Benefitted from its great success on many tasks, deep learning is increasingly used on low-computational-cost devices, e.g. smartphone, embedded devices, etc. To reduce the high computational and memory cost, in this work, we propose a fully learnable group convolution module (FLGC for short) which is quite efficient and can be embedded into any deep neural networks for acceleration. Specifically, our proposed method automatically learns the group structure in the training stage in a fully end-to-end manner, leading to a better structure than the existing pre-defined, two-steps, or iterative strategies. Moreover, our method can be further combined with depthwise separable convolution, resulting in 5 times acceleration than the vanilla Resnet50 on single CPU. An additional advantage is that in our FLGC the number of groups can be set as any value, but not necessarily 2^k as in most existing methods, meaning better tradeoff between accuracy and speed. As evaluated in our experiments, our method achieves better performance than existing learnable group convolution and standard group convolution when using the same number of groups.
Fully Polynomial-Time Approximation Scheme
We consider the product knapsack problem, which is the variant of the classical 0-1 knapsack problem where the objective consists of maximizing the product of the profits of the selected items. These profits are allowed to be positive or negative. We show that this recently introduced variant of the knapsack problem is weakly NP-hard and present a fully polynomial-time approximation scheme (FPTAS) for the problem. Moreover, we analyze the approximation quality achieved by a natural extension of the classical greedy procedure to the product knapsack problem.
Fully-Trained Generative Adversarial Network
As a sub-domain of text-to-image synthesis, text-to-face generation has huge potentials in public safety domain. With lack of dataset, there are almost no related research focusing on text-to-face synthesis. In this paper, we propose a fully-trained Generative Adversarial Network (FTGAN) that trains the text encoder and image decoder at the same time for fine-grained text-to-face generation. With a novel fully-trained generative network, FTGAN can synthesize higher-quality images and urge the outputs of the FTGAN are more relevant to the input sentences. In addition, we build a dataset called SCU-Text2face for text-to-face synthesis. Through extensive experiments, the FTGAN shows its superiority in boosting both generated images’ quality and similarity to the input descriptions. The proposed FTGAN outperforms the previous state of the art, boosting the best reported Inception Score to 4.63 on the CUB dataset. On SCU-text2face, the face images generated by our proposed FTGAN just based on the input descriptions is of average 59% similarity to the ground-truth, which set a baseline for text-to-face synthesis.
Functional Additive Regression
We suggest a new method, called Functional Additive Regression, or FAR, for efficiently performing high-dimensional functional regression. FAR extends the usual linear regression model involving a functional predictor, $X(t)$, and a scalar response, $Y$, in two key respects. First, FAR uses a penalized least squares optimization approach to efficiently deal with high-dimensional problems involving a large number of functional predictors. Second, FAR extends beyond the standard linear regression setting to fit general nonlinear additive models. We demonstrate that FAR can be implemented with a wide range of penalty functions using a highly efficient coordinate descent algorithm. Theoretical results are developed which provide motivation for the FAR optimization criterion. Finally, we show through simulations and two real data sets that FAR can significantly outperform competing methods.
Functional Aggregate Queries
Motivated by fundamental applications in databases and relational machine learning, we formulate and study the problem of answering Functional Aggregate Queries (FAQ) in which some of the input factors are defined by a collection of Additive Inequalities between variables. We refer to these queries as FAQ-AI for short. To answer FAQ-AI in the Boolean semiring, we define ‘relaxed’ tree decompositions and ‘relaxed’ submodular and fractional hypertree width parameters. We show that an extension of the InsideOut algorithm using Chazelle’s geometric data structure for solving the semigroup range search problem can answer Boolean FAQ-AI in time given by these new width parameters. This new algorithm achieves lower complexity than known solutions for FAQ-AI. It also recovers some known results in database query answering. Our second contribution is a relaxation of the set of polymatroids that gives rise to the counting version of the submodular width, denoted by ‘#subw’. This new width is sandwiched between the submodular and the fractional hypertree widths. Any FAQ and FAQ-AI over one semiring can be answered in time proportional to #subw and respectively to the relaxed version of #subw. We present three applications of our FAQ-AI framework to relational machine learning: k-means clustering, training linear support vector machines, and training models using non-polynomial loss. These optimization problems can be solved over a database asymptotically faster than computing the join of the database relations.
Functional Average Variance Estimation
We propose an estimation method that we call functional average variance estimation (FAVE), for estimating the EDR space in functional semiparametric regression model, based on kernel estimates of density and regression. Consistency results are then established for the estimator of the interest operator, and for the directions of EDR space. A simulation study that shows that the proposed approach performs as well as traditional ones is presented.
Functional Causal Model
Functional Data Analysis
Functional data analysis is a branch of statistics that analyzes data providing information about curves, surfaces or anything else varying over a continuum. The continuum is often time, but may also be spatial location, wavelength, probability, etc.
Functional Decision Theory This paper describes and motivates a new decision theory known as functional decision theory (FDT), as distinct from causal decision theory and evidential decision theory. Functional decision theorists hold that the normative principle for action is to treat one’s decision as the output of a fixed mathematical function that answers the question, ‘Which output of this very function would yield the best outcome?’ Adhering to this principle delivers a number of benefits, including the ability to maximize wealth in an array of traditional decision-theoretic and game-theoretic problems where CDT and EDT perform poorly. Using one simple and coherent decision rule, functional decision theorists (for example) achieve more utility than CDT on Newcomb’s problem, more utility than EDT on the smoking lesion problem, and more utility than both in Parfit’s hitchhiker problem. In this paper, we define FDT, explore its prescriptions in a number of different decision problems, compare it to CDT and EDT, and give philosophical justifications for FDT as a normative theory of decision-making.
Functional Dynamic Principle Components Analysis freqdom.fda
Functional Intrusive Load Monitor
Non-Intrusive Load Monitoring (NILM) is an important application to monitor household appliance activities and provide related information to house owner or/and utility company via a single sensor installed at the electrical entry of the house. It can be used for different purposes in residential and industrial sectors. Thus, an increasing number of new algorithms have been developed in recent years. In these algorithms, researchers either use existing public datasets or collect their own data which causes such problems as insufficiency of electrical parameters, missing of ground-truth data, absence of many appliances, and lack of appliance information. To solve these problems, this paper presents a model-based platform for NILM system development, namely Functional Intrusive Load Monitor (FILM). By using this platform, the state transitions and activities of all the involved appliances can be preset by researchers, and multiple electrical parameters such as harmonics and power factor can be monitored or calculated. This platform will help researchers save the time of collecting experimental data, utilize precise control of individual appliance activities, and develop load signatures of devices. This paper describes the steps, structure, and requirements of building this platform. Case study is presented to help understand this platform.
Functional Isolation Forest
For the purpose of monitoring the behavior of complex infrastructures (e.g. aircrafts, transport or energy networks), high-rate sensors are deployed to capture multivariate data, generally unlabeled, in quasi continuous-time to detect quickly the occurrence of anomalies that may jeopardize the smooth operation of the system of interest. The statistical analysis of such massive data of functional nature raises many challenging methodological questions. The primary goal of this paper is to extend the popular Isolation Forest (IF) approach to Anomaly Detection, originally dedicated to finite dimensional observations, to functional data. The major difficulty lies in the wide variety of topological structures that may equip a space of functions and the great variety of patterns that may characterize abnormal curves. We address the issue of (randomly) splitting the functional space in a flexible manner in order to isolate progressively any trajectory from the others, a key ingredient to the efficiency of the algorithm. Beyond a detailed description of the algorithm, computational complexity and stability issues are investigated at length. From the scoring function measuring the degree of abnormality of an observation provided by the proposed variant of the IF algorithm, a Functional Statistical Depth function is defined and discussed as well as a multivariate functional extension. Numerical experiments provide strong empirical evidence of the accuracy of the extension proposed.
Functional Linear Array Model
The functional linear array model (FLAM) is a unified model class for functional regression models including function-on-scalar, scalar-on-function and function-on-function regression. Mean, median, quantile as well as generalized additive regression models for functional or scalar responses are contained as special cases in this general framework. Our implementation features a broad variety of covariate effects, such as, linear, smooth and interaction effects of grouping variables, scalar and functional covariates. Computational efficiency is achieved by representing the model as a generalized linear array model. While the array structure requires a common grid for functional responses, missing values are allowed. Estimation is conducted using a boosting algorithm, which allows for numerous covariates and automatic, data-driven model selection. To illustrate the flexibility of the model class we use three applications on curing of resin for car production, heat values of fossil fuels and Canadian climate data (the last one in the electronic supplement). These require function-on-scalar, scalar-on-function and function-on-function regression models, respectively, as well as additional capabilities such as robust regression, spatial functional regression, model selection and accommodation of missings. An implementation of our methods is provided in the R add-on package FDboost.
Functional Multilayer Perceptron
(Functional MLP)
Remaining Useful Life (RUL) of an equipment or one of its components is defined as the time left until the equipment or component reaches its end of useful life. Accurate RUL estimation is exceptionally beneficial to Predictive Maintenance, and Prognostics and Health Management (PHM). Data driven approaches which leverage the power of algorithms for RUL estimation using sensor and operational time series data are gaining popularity. Existing algorithms, such as linear regression, Convolutional Neural Network (CNN), Hidden Markov Models (HMMs), and Long Short-Term Memory (LSTM), have their own limitations for the RUL estimation task. In this work, we propose a novel Functional Data Analysis (FDA) method called functional Multilayer Perceptron (functional MLP) for RUL estimation. Functional MLP treats time series data from multiple equipment as a sample of random continuous processes over time. FDA explicitly incorporates both the correlations within the same equipment and the random variations across different equipment’s sensor time series into the model. FDA also has the benefit of allowing the relationship between RUL and sensor variables to vary over time. We implement functional MLP on the benchmark NASA C-MAPSS data and evaluate the performance using two popularly-used metrics. Results show the superiority of our algorithm over all the other state-of-the-art methods.
Functional Principal Component Analysis
Functional principal component analysis (FPCA) is a statistical method for investigating the dominant modes of variation of functional data. Using this method, a random function is represented in the eigenbasis, which is an orthonormal basis of the Hilbert space L2 that consists of the eigenfunctions of the autocovariance operator. FPCA represents functional data in the most parsimonious way, in the sense that when using a fixed number of basis functions, the eigenfunction basis explains more variation than any other basis expansion. FPCA can be applied for representing random functions, or functional regression and classification.
Functional Regression This paper deals with functional regression, in which the input attributes as well as the response are functions. To deal with this problem, we develop a functional reproducing kernel Hilbert space approach; here, a kernel is an operator acting on a function and yielding a function. We demonstrate basic properties of these functional RKHS, as well as a representer theorem for this setting; we investigate the construction of kernels; we provide some experimental insight.
A General Theory for Large-Scale Curve Time Series via Functional Stability Measure
Functional Target Controllability In this paper we consider the problem of controlling a limited number of target nodes of a network. Equivalently, we can see this problem as controlling the target variables of a structured system, where the state variables of the system are associated to the nodes of the network. We deal with this problem from a different point of view as compared to most recent literature. Indeed, instead of considering controllability in the Kalman sense, that is, as the ability to drive the target states to a desired value, we consider the stronger requirement of driving the target variables as time functions. The latter notion is called functional target controllability. We think that restricting the controllability requirement to a limited set of important variables justifies using a more accurate notion of controllability for these variables. Remarkably, the notion of functional controllability allows formulating very simple graphical conditions for target controllability, in the spirit of the structural approach to controllability. The functional approach enables us, moreover, to determine the smallest set of steering nodes that need to be actuated to ensure target controllability, where these steering nodes are constrained to belong to a given set. We show that such a smallest set can be found in polynomial time. We are also able to classify the possible actuated variables in terms of their importance with respect to the functional target controllability problem.
Functional Time Series
Functional Variational Bayesian Neural Network
Variational Bayesian neural networks (BNNs) perform variational inference over weights, but it is difficult to specify meaningful priors and approximate posteriors in a high-dimensional weight space. We introduce functional variational Bayesian neural networks (fBNNs), which maximize an Evidence Lower BOund (ELBO) defined directly on stochastic processes, i.e. distributions over functions. We prove that the KL divergence between stochastic processes equals the supremum of marginal KL divergences over all finite sets of inputs. Based on this, we introduce a practical training objective which approximates the functional ELBO using finite measurement sets and the spectral Stein gradient estimator. With fBNNs, we can specify priors entailing rich structures, including Gaussian processes and implicit stochastic processes. Empirically, we find fBNNs extrapolate well using various structured priors, provide reliable uncertainty estimates, and scale to large datasets.
Fundamental Theorem of Linear Algebra In mathematics, the fundamental theorem of linear algebra makes several statements regarding vector spaces. These may be stated concretely in terms of the rank r of an m x n matrix A and its singular value decomposition.
funFEM A novel model-based clustering method for time series (and more generally functional data), called FunFEM. It is based on the discriminative functional mixture (DFM) model which models the data into a single discriminative functional subspace. This subspace allows afterward an insightful visualizations of the clustered data.
funHDDC General procedure for clustering functional data which adapts the efficient clustering method HDDC, originally proposed in the multivariate context. The resulting clustering method, called funHDDC, is based on a functional latent mixture model which fits the functional data in group-specific functional subspaces. By constraining model parameters within and between groups, a family of parsimonious models is exhibited which allow to fit onto various situations. An estimation procedure based on the EM algorithm is proposed for estimating both the model parameters and the group-specific functional subspaces. Experiments on real-world datasets show that the proposed approach performs better or similarly than classical clustering methods while providing useful interpretations of the groups.
Funnelling Polylingual Text Classification (PLC) consists of automatically classifying, according to a common set C of classes, documents each written in one of a set of languages L, and doing so more accurately than when naively classifying each document via its corresponding language-specific classifier. In order to obtain an increase in the classification accuracy for a given language, the system thus needs to also leverage the training examples written in the other languages. We tackle multilabel PLC via funnelling, a new ensemble learning method that we propose here. Funnelling consists of generating a two-tier classification system where all documents, irrespectively of language, are classified by the same (2nd-tier) classifier. For this classifier all documents are represented in a common, language-independent feature space consisting of the posterior probabilities generated by 1st-tier, language-dependent classifiers. This allows the classification of all test documents, of any language, to benefit from the information present in all training documents, of any language. We present substantial experiments, run on publicly available polylingual text collections, in which funnelling is shown to significantly outperform a number of state-of-the-art baselines. All code and datasets (in vector form) are made publicly available.
Furcated Neural Network “IL-Net”
Fused Gromov-Wasserstein Distance Optimal transport has recently gained a lot of interest in the machine learning community thanks to its ability to compare probability distributions while respecting the underlying space’s geometry. Wasserstein distance deals with feature information through its metric or cost function, but fails in exploiting the structural information, i.e the specific relations existing among the components of the distribution. Recently adapted to a machine learning context, the Gromov-Wasserstein distance defines a metric well suited for comparing distributions that live in different metric spaces by exploiting their inner structural information. In this paper we propose a new optimal transport distance, called the Fused Gromov-Wasserstein distance, capable of leveraging both structural and feature information by combining both views and prove its metric properties over very general manifolds. We also define the barycenter of structured objects as their Fr\’echet mean, leveraging both feature and structural information. We illustrate the versatility of the method for problems where structured objects are involved, computing barycenters in graph and time series contexts. We also use this new distance for graph classification where we obtain comparable or superior results than state-of-the-art graph kernel methods and end-to-end graph CNN approach.
Fused Lasso Feature selection has been proven a powerful preprocessing step for high-dimensional data analysis. However, most state-of-the-art methods suffer from two major drawbacks. First, they usually overlook the structural correlation information between pairwise samples, which may encapsulate useful information for refining the performance of feature selection. Second, they usually consider candidate feature relevancy equivalent to selected feature relevancy, and some less relevant features may be misinterpreted as salient features. To overcome these issues, we propose a new fused lasso for feature selection using structural information. Our idea is based on converting the original vectorial features into structure-based feature graph representations to incorporate structural relationship between samples, and defining a new evaluation measure to compute the joint significance of pairwise feature combinations in relation to the target feature graph. Furthermore, we formulate the corresponding feature subset selection problem into a least square regression model associated with a fused lasso regularizer to simultaneously maximize the joint relevancy and minimize the redundancy of the selected features. To effectively solve the challenging optimization problem, an iterative algorithm is developed to identify the most discriminative features. Experiments demonstrate the effectiveness of the proposed approach.
FusedGAN We present FusedGAN, a deep network for conditional image synthesis with controllable sampling of diverse images. Fidelity, diversity and controllable sampling are the main quality measures of a good image generation model. Most existing models are insufficient in all three aspects. The FusedGAN can perform controllable sampling of diverse images with very high fidelity. We argue that controllability can be achieved by disentangling the generation process into various stages. In contrast to stacked GANs, where multiple stages of GANs are trained separately with full supervision of labeled intermediate images, the FusedGAN has a single stage pipeline with a built-in stacking of GANs. Unlike existing methods, which requires full supervision with paired conditions and images, the FusedGAN can effectively leverage more abundant images without corresponding conditions in training, to produce more diverse samples with high fidelity. We achieve this by fusing two generators: one for unconditional image generation, and the other for conditional image generation, where the two partly share a common latent space thereby disentangling the generation. We demonstrate the efficacy of the FusedGAN in fine grained image generation tasks such as text-to-image, and attribute-to-face generation.
Fusion Discriminator We propose the fusion discriminator, a single unified framework for incorporating conditional information into a generative adversarial network (GAN) for a variety of distinct structured prediction tasks, including image synthesis, semantic segmentation, and depth estimation. Much like commonly used convolutional neural network — conditional Markov random field (CNN-CRF) models, the proposed method is able to enforce higher-order consistency in the model, but without being limited to a very specific class of potentials. The method is conceptually simple and flexible, and our experimental results demonstrate improvement on several diverse structured prediction tasks.
Fusion Graph Convolutional Network Semi-supervised node classification involves learning to classify unlabelled nodes given a partially labeled graph. In transductive learning, all unlabelled nodes to be classified are observed during training and in inductive learning, predictions are to be made for nodes not seen at training. In this paper, we focus on both these settings for node classification in attributed graphs, i.e., graphs in which nodes have additional features. State-of-the-art models for node classification on such attributed graphs use differentiable recursive functions. These differentiable recursive functions enable aggregation and filtering of neighborhood information from multiple hops (depths). Despite being powerful, these variants are limited in their ability to combine information from different hops efficiently. In this work, we analyze this limitation of recursive graph functions in terms of their representation capacity to effectively capture multi-hop neighborhood information. Further, we provide a simple fusion component which is mathematically motivated to address this limitation and improve the existing models to explicitly learn the importance of information from different hops. This proposed mechanism is shown to improve over existing methods across 8 popular datasets from different domains. Specifically, our model improves the Graph Convolutional Network (GCN) and a variant of Graph SAGE by a significant margin providing highly competitive state-of-the-art results.
Fusion Hashing
Hashing has been widely used for efficient similarity search based on its query and storage efficiency. To obtain better precision, most studies focus on designing different objective functions with different constraints or penalty terms that consider neighborhood information. In this paper, in contrast to existing hashing methods, we propose a novel generalized framework called fusion hashing (FH) to improve the precision of existing hashing methods without adding new constraints or penalty terms. In the proposed FH, given an existing hashing method, we first execute it several times to get several different hash codes for a set of training samples. We then propose two novel fusion strategies that combine these different hash codes into one set of final hash codes. Based on the final hash codes, we learn a simple linear hash function for the samples that can significantly improve model precision. In general, the proposed FH can be adopted in existing hashing method and achieve more precise and stable performance compared to the original hashing method with little extra expenditure in terms of time and space. Extensive experiments were performed based on three benchmark datasets and the results demonstrate the superior performance of the proposed framework
Fusion Subspace Clustering Modern inference and learning often hinge on identifying low-dimensional structures that approximate large scale data. Subspace clustering achieves this through a union of linear subspaces. However, in contemporary applications data is increasingly often incomplete, rendering standard (full-data) methods inapplicable. On the other hand, existing incomplete-data methods present major drawbacks, like lifting an already high-dimensional problem, or requiring a super polynomial number of samples. Motivated by this, we introduce a new subspace clustering algorithm inspired by fusion penalties. The main idea is to permanently assign each datum to a subspace of its own, and minimize the distance between the subspaces of all data, so that subspaces of the same cluster get fused together. Our approach is entirely new to both, full and missing data, and unlike other methods, it directly allows noise, it requires no liftings, it allows low, high, and even full-rank data, it approaches optimal (information-theoretic) sampling rates, and it does not rely on other methods such as low-rank matrix completion to handle missing data. Furthermore, our extensive experiments on both real and synthetic data show that our approach performs comparably to the state-of-the-art with complete data, and dramatically better if data is missing.
Future In computer science, future, promise, and delay refer to constructs used for synchronization in some concurrent programming languages. They describe an object that acts as a proxy for a result that is initially unknown, usually because the computation of its value is yet incomplete. The term promise was proposed in 1976 by Daniel P. Friedman and David Wise, and Peter Hibbard called it eventual. A somewhat similar concept future was introduced in 1977 in a paper by Henry Baker and Carl Hewitt. The terms future, promise, and delay are often used interchangeably, although some differences in usage between future and promise are treated below. Specifically, when usage is distinguished, a future is a read-only placeholder view of a variable, while a promise is a writable, single assignment container which sets the value of the future. Notably, a future may be defined without specifying which specific promise will set its value, and different possible promises may set the value of a given future, though this can be done only once for a given future. In other cases a future and a promise are created together and associated with each other: the future is the value, the promise is the function that sets the value – essentially the return value (future) of an asynchronous function (promise). Setting the value of a future is also called resolving, fulfilling, or binding it.
Future Environment Inference
In Business Intelligence, accurate predictive modeling is the key for providing adaptive decisions. We studied predictive modeling problems in this research which was motivated by real-world cases that Microsoft data scientists encountered while dealing with e-commerce transaction fraud control decisions using transaction streaming data in an uncertain probabilistic decision environment. The values of most online transactions related features can return instantly, while the true fraud labels only return after a stochastic delay. Using partially mature data directly for predictive modeling in an uncertain probabilistic decision environment would lead to significant inaccuracy on risk decision-making. To improve accurate estimation of the probabilistic prediction environment, which leads to more accurate predictive modeling, two frameworks, Current Environment Inference (CEI) and Future Environment Inference (FEI), are proposed. These frameworks generated decision environment related features using long-term fully mature and short-term partially mature data, and the values of those features were estimated using varies of learning methods, including linear regression, random forest, gradient boosted tree, artificial neural network, and recurrent neural network. Performance tests were conducted using some e-commerce transaction data from Microsoft. Testing results suggested that proposed frameworks significantly improved the accuracy of decision environment estimation.
Future-State Predicting LSTM This work presents a novel approach for the early recognition of the type of a laparoscopic surgery from its video. Early recognition algorithms can be beneficial to the development of ‘smart’ OR systems that can provide automatic context-aware assistance, and also enable quick database indexing. The task is however ridden with challenges specific to videos belonging to the domain of laparoscopy, such as high visual similarity across surgeries and large variations in video durations. To capture the spatio-temporal dependencies in these videos, we choose as our model a combination of a Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) network. We then propose two complementary approaches for improving early recognition performance. The first approach is a CNN fine-tuning method that encourages surgeries to be distinguished based on the initial frames of laparoscopic videos. The second approach, referred to as ‘Future-State Predicting LSTM’, trains an LSTM to predict information related to future frames, which helps in distinguishing between the different types of surgeries. We evaluate our approaches on a large dataset of 425 laparoscopic videos containing 9 types of surgeries (Laparo425), and achieve on average an accuracy of 75% having observed only the first 10 minutes of a surgery. These results are quite promising from a practical standpoint and also encouraging for other types of image-guided surgeries.
FuzzerGym Fuzzing is a commonly used technique designed to test software by automatically crafting program inputs. Currently, the most successful fuzzing algorithms emphasize simple, low-overhead strategies with the ability to efficiently monitor program state during execution. Through compile-time instrumentation, these approaches have access to numerous aspects of program state including coverage, data flow, and heterogeneous fault detection and classification. However, existing approaches utilize blind random mutation strategies when generating test inputs. We present a different approach that uses this state information to optimize mutation operators using reinforcement learning (RL). By integrating OpenAI Gym with libFuzzer we are able to simultaneously leverage advancements in reinforcement learning as well as fuzzing to achieve deeper coverage across several varied benchmarks. Our technique connects the rich, efficient program monitors provided by LLVM Santizers with a deep neural net to learn mutation selection strategies directly from the input data. The cross-language, asynchronous architecture we developed enables us to apply any OpenAI Gym compatible deep reinforcement learning algorithm to any fuzzing problem with minimal slowdown.
Fuzzing Fuzzing or fuzz testing is an automated software testing technique that involves providing invalid, unexpected, or random data as inputs to a computer program. The program is then monitored for exceptions such as crashes, failing built-in code assertions, or potential memory leaks. Typically, fuzzers are used to test programs that take structured inputs. This structure is specified, e.g., in a file format or protocol and distinguishes valid from invalid input. An effective fuzzer generates semi-valid inputs that are ‘valid enough’ in that they are not directly rejected by the parser, but do create unexpected behaviors deeper in the program and are ‘invalid enough’ to expose corner cases that have not been properly dealt with. For the purpose of security, input that crosses a trust boundary is often the most interesting.[1] For example, it is more important to fuzz code that handles the upload of a file by any user than it is to fuzz the code that parses a configuration file that is accessible only to a privileged user.
Fuzzing: Art, Science, and Engineering
Fuzzy bag-of-Words
Recent literature suggests that averaged word vectors followed by simple post-processing outperform many deep learning methods on semantic textual similarity tasks. Furthermore, when averaged word vectors are trained supervised on large corpora of paraphrases, they achieve state-of-the-art results on standard STS benchmarks. Inspired by these insights, we push the limits of word embeddings even further. We propose a novel fuzzy bag-of-words (FBoW) representation for text that contains all the words in the vocabulary simultaneously but with different degrees of membership, which are derived from similarities between word vectors. We show that max-pooled word vectors are only a special case of fuzzy BoW and should be compared via fuzzy Jaccard index rather than cosine similarity. Finally, we propose DynaMax, a completely unsupervised and non-parametric similarity measure that dynamically extracts and max-pools good features depending on the sentence pair. This method is both efficient and easy to implement, yet outperforms current baselines on STS tasks by a large margin and is even competitive with supervised word vectors trained to directly optimise cosine similarity.
Fuzzy Bayesian Learning In this paper we propose a novel approach for learning from data using rule based fuzzy inference systems where the model parameters are estimated using Bayesian inference and Markov Chain Monte Carlo (MCMC) techniques. We show the applicability of the method for regression and classification tasks using synthetic data-sets and also a real world example in the financial services industry. Then we demonstrate how the method can be extended for knowledge extraction to select the individual rules in a Bayesian way which best explains the given data. Finally we discuss the advantages and pitfalls of using this method over state-of-the-art techniques and highlight the specific class of problems where this would be useful.
Fuzzy Clustering Fuzzy clustering is a class of algorithms for cluster analysis in which the allocation of data points to clusters is not “hard” (all-or-nothing) but “fuzzy” in the same sense as fuzzy logic.
Fuzzy clustering by Local Approximation of MEmberships Clustering
Fuzzy clustering by Local Approximation of MEmberships (FLAME) is a data clustering algorithm that defines clusters in the dense parts of a dataset and performs cluster assignment solely based on the neighborhood relationships among objects. The key feature of this algorithm is that the neighborhood relationships among neighboring objects in the feature space are used to constrain the memberships of neighboring objects in the fuzzy membership space.
Fuzzy C-Means Clustering
In fuzzy clustering, every point has a degree of belonging to clusters, as in fuzzy logic, rather than belonging completely to just one cluster. Thus, points on the edge of a cluster, may be in the cluster to a lesser degree than points in the center of cluster.
Any point x has a set of coefficients giving the degree of being in the kth cluster wk(x). With fuzzy c-means, the centroid of a cluster is the mean of all points, weighted by their degree of belonging to the cluster.
Fuzzy Cognitive Map A Fuzzy cognitive map is a cognitive map within which the relations between the elements (e.g. concepts, events, project resources) of a ‘mental landscape’ can be used to compute the ‘strength of impact’ of these elements. The theory behind that computation is fuzzy logic.
Short-term Cognitive Networks, Flexible Reasoning and Nonsynaptic Learning
Fuzzy Constraint Linear Discriminant Analysis
In this paper we introduce a fuzzy constraint linear discriminant analysis (FC-LDA). The FC-LDA tries to minimize misclassification error based on modified perceptron criterion that benefits handling the uncertainty near the decision boundary by means of a fuzzy linear programming approach with fuzzy resources. The method proposed has low computational complexity because of its linear characteristics and the ability to deal with noisy data with different degrees of tolerance. Obtained results verify the success of the algorithm when dealing with different problems. Comparing FC-LDA and LDA shows superiority in classification task.
Fuzzy GP Reinforcement Learning
Autonomously training interpretable control strategies, called policies, using pre-existing plant trajectory data is of great interest in industrial applications. Fuzzy controllers have been used in industry for decades as interpretable and efficient system controllers. In this study, we introduce a fuzzy genetic programming (GP) approach called fuzzy GP reinforcement learning (FGPRL) that can select the relevant state features, determine the size of the required fuzzy rule set, and automatically adjust all the controller parameters simultaneously. Each GP individual’s fitness is computed using model-based batch reinforcement learning (RL), which first trains a model using available system samples and subsequently performs Monte Carlo rollouts to predict each policy candidate’s performance. We compare FGPRL to an extended version of a related method called fuzzy particle swarm reinforcement learning (FPSRL), which uses swarm intelligence to tune the fuzzy policy parameters. Experiments using an industrial benchmark show that FGPRL is able to autonomously learn interpretable fuzzy policies with high control performance.
Fuzzy ROC The fuzzy ROC extends Receiver Operating Curve (ROC) visualization to the situation where some data points, falling in an indeterminacy region, are not classified. It addresses two challenges: definition of sensitivity and specificity bounds under indeterminacy; and visual summarization of the large number of possibilities arising from different choices of indeterminacy zones.
Fuzzy Rule Interpolation
A way for fuzzy inference by interpolation of the existing fuzzy rules based on various distance and similarity measures of fuzzy sets. A suitable method for handling sparse fuzzy rule bases, since FRI methods can provide reasonable (interpolated/extrapolated) conclusions even if none of the existing rules fires under the current observation.
Fuzzy Rule Interpolation Methods and Fri Toolbox
Fuzzy SAINTETIQ Diversification of DB applications highlighted the limitations of relational database management system (RDBMS) particularly on the modeling plan. In fact, in the real world, we are increasingly faced with the situation where applications need to handle imprecise data and to offer a flexible querying to their users. Several theoretical solutions have been proposed. However, the impact of this work in practice remained negligible with the exception of a few research prototypes based on the formal model GEFRED. In this chapter, the authors propose a new approach for exploitation of fuzzy relational databases (FRDB) described by the model GEFRED. This approach consists of 1) a new technique for extracting summary fuzzy data, Fuzzy SAINTETIQ, based on the classification of fuzzy data and formal concepts analysis; 2) an approach of assessing flexible queries in the context of FDB based on the set of fuzzy summaries generated by our fuzzy SAINTETIQ system; 3) an approach of repairing and substituting unanswered query.
Fuzzy Supervised Learning with Binary Meta-Feature
This paper introduces a novel real-time Fuzzy Supervised Learning with Binary Meta-Feature (FSL-BM) for big data classification task. The study of real-time algorithms addresses several major concerns, which are namely: accuracy, memory consumption, and ability to stretch assumptions and time complexity. Attaining a fast computational model providing fuzzy logic and supervised learning is one of the main challenges in the machine learning. In this research paper, we present FSL-BM algorithm as an efficient solution of supervised learning with fuzzy logic processing using binary meta-feature representation using Hamming Distance and Hash function to relax assumptions. While many studies focused on reducing time complexity and increasing accuracy during the last decade, the novel contribution of this proposed solution comes through integration of Hamming Distance, Hash function, binary meta-features, binary classification to provide real time supervised method. Hash Tables (HT) component gives a fast access to existing indices; and therefore, the generation of new indices in a constant time complexity, which supersedes existing fuzzy supervised algorithms with better or comparable results. To summarize, the main contribution of this technique for real-time Fuzzy Supervised Learning is to represent hypothesis through binary input as meta-feature space and creating the Fuzzy Supervised Hash table to train and validate model.
f-VAE In this paper, we integrate VAEs and flow-based generative models successfully and get f-VAEs. Compared with VAEs, f-VAEs generate more vivid images, solved the blurred-image problem of VAEs. Compared with flow-based models such as Glow, f-VAE is more lightweight and converges faster, achieving the same performance under smaller-size architecture.