Surrogate Objective Function
Influence maximization has found applications in a wide range of real-world problems, for instance, viral marketing of products in an online social network, and information propagation of valuable information such as job vacancy advertisements and health-related information. While existing algorithmic techniques usually aim at maximizing the total number of people influenced, the population often comprises several socially salient groups, e.g., based on gender or race. As a result, these techniques could lead to disparity across different groups in receiving important information. Furthermore, in many of these applications, the spread of influence is time-critical, i.e., it is only beneficial to be influenced before a time deadline. As we show in this paper, the time-criticality of the information could further exacerbate the disparity of influence across groups. This disparity, introduced by algorithms aimed at maximizing total influence, could have far-reaching consequences, impacting people’s prosperity and putting minority groups at a big disadvantage. In this work, we propose a notion of group fairness in time-critical influence maximization. We introduce surrogate objective functions to solve the influence maximization problem under fairness considerations. By exploiting the submodularity structure of our objectives, we provide computationally efficient algorithms with guarantees that are effective in enforcing fairness during the propagation process. We demonstrate the effectiveness of our approach through synthetic and real-world experiments. …

Max of Weighed Distance (MWD)
Adversarial attacks add perturbations to the input features with the intent of changing the classification produced by a machine learning system. Small perturbations can yield adversarial examples which are misclassified despite being virtually indistinguishable from the unperturbed input. Classifiers trained with standard neural network techniques are highly susceptible to adversarial examples, allowing an adversary to create misclassifications of their choice. We introduce a new type of network unit, called MWD (max of weighed distance) units that have a built-in resistant to adversarial attacks. These units are highly non-linear, and we develop the techniques needed to effectively train them. We show that simple interval techniques for propagating perturbation effects through the network enables the efficient computation of robustness (i.e., accuracy guarantees) for MWD networks under any perturbations, including adversarial attacks. MWD networks are significantly more robust to input perturbations than ReLU networks. On permutation invariant MNIST, when test examples can be perturbed by 20% of the input range, MWD networks provably retain accuracy above 83%, while the accuracy of ReLU networks drops below 5%. The provable accuracy of MWD networks is superior even to the observed accuracy of ReLU networks trained with the help of adversarial examples. In the absence of adversarial attacks, MWD networks match the performance of sigmoid networks, and have accuracy only slightly below that of ReLU networks. …

ADaPTION Toolbox
Deep Neural Networks (DNNs) and Convolutional Neural Networks (CNNs) are useful for many practical tasks in machine learning. Synaptic weights, as well as neuron activation functions within the deep network are typically stored with high-precision formats, e.g. 32 bit floating point. However, since storage capacity is limited and each memory access consumes power, both storage capacity and memory access are two crucial factors in these networks. Here we present a method and present the ADaPTION toolbox to extend the popular deep learning library Caffe to support training of deep CNNs with reduced numerical precision of weights and activations using fixed point notation. ADaPTION includes tools to measure the dynamic range of weights and activations. Using the ADaPTION tools, we quantized several CNNs including VGG16 down to 16-bit weights and activations with only 0.8% drop in Top-1 accuracy. The quantization, especially of the activations, leads to increase of up to 50% of sparsity especially in early and intermediate layers, which we exploit to skip multiplications with zero, thus performing faster and computationally cheaper inference. …

Automatic BAyesian Changepoints Under Sparsity (ABACUS)
Change detection involves segmenting sequential data such that observations in the same segment share some desired properties. Multivariate change detection continues to be a challenging problem due to the variety of ways change points can be correlated across channels and the potentially poor signal-to-noise ratio on individual channels. In this paper, we are interested in locating additive outliers (AO) and level shifts (LS) in the unsupervised setting. We propose ABACUS, Automatic BAyesian Changepoints Under Sparsity, a Bayesian source separation technique to recover latent signals while also detecting changes in model parameters. Multi-level sparsity achieves both dimension reduction and modeling of signal changes. We show ABACUS has competitive or superior performance in simulation studies against state-of-the-art change detection methods and established latent variable models. We also illustrate ABACUS on two real application, modeling genomic profiles and analyzing household electricity consumption. …

MMALFM
Although the latent factor model achieves good accuracy in rating prediction, it suffers from many problems including cold-start, non-transparency, and suboptimal results for individual user-item pairs. In this paper, we exploit textual reviews and item images together with ratings to tackle these limitations. Specifically, we first apply a proposed multi-modal aspect-aware topic model (MATM) on text reviews and item images to model users’ preferences and items’ features from different aspects, and also estimate the aspect importance of a user towards an item. Then the aspect importance is integrated into a novel aspect-aware latent factor model (ALFM), which learns user’s and item’s latent factors based on ratings. In particular, ALFM introduces a weight matrix to associate those latent factors with the same set of aspects in MATM, such that the latent factors could be used to estimate aspect ratings. Finally, the overall rating is computed via a linear combination of the aspect ratings, which are weighted by the corresponding aspect importance. To this end, our model could alleviate the data sparsity problem and gain good interpretability for recommendation. Besides, every aspect rating is weighted by its aspect importance, which is dependent on the targeted user’s preferences and the targeted item’s features. Therefore, it is expected that the proposed method can model a user’s preferences on an item more accurately for each user-item pair. Comprehensive experimental studies have been conducted on the Yelp 2017 Challenge dataset and Amazon product datasets to demonstrate the effectiveness of our method. …

WikiLinkGraphs
Wikipedia articles contain multiple links connecting a subject to other pages of the encyclopedia. In Wikipedia parlance, these links are called internal links or wikilinks. We present a complete dataset of the network of internal Wikipedia links for the $9$ largest language editions. The dataset contains yearly snapshots of the network and spans $17$ years, from the creation of Wikipedia in 2001 to March 1st, 2018. While previous work has mostly focused on the complete hyperlink graph which includes also links automatically generated by templates, we parsed each revision of each article to track links appearing in the main text. In this way we obtained a cleaner network, discarding more than half of the links and representing all and only the links intentionally added by editors. We describe in detail how the Wikipedia dumps have been processed and the challenges we have encountered, including the need to handle special pages such as redirects, i.e., alternative article titles. We present descriptive statistics of several snapshots of this network. Finally, we propose several research opportunities that can be explored using this new dataset. …

Apache Oozie
Oozie is a workflow scheduler system to manage Apache Hadoop jobs. Oozie is integrated with the rest of the Hadoop stack supporting several types of Hadoop jobs out of the box (such as Java map-reduce, Streaming map-reduce, Pig, Hive, Sqoop and Distcp) as well as system specific jobs (such as Java programs and shell scripts). …

Semi-Implicit Generator (SIG)
To combine explicit and implicit generative models, we introduce semi-implicit generator (SIG) as a flexible hierarchical model that can be trained in the maximum likelihood framework. Both theoretically and experimentally, we demonstrate that SIG can generate high quality samples especially when dealing with multi-modality. By introducing SIG as an unbiased regularizer to the generative adversarial network (GAN), we show the interplay between maximum likelihood and adversarial learning can stabilize the adversarial training, resist the notorious mode collapsing problem of GANs, and improve the diversity of generated random samples. …

Landmark Retracing Network (LRN)
Since convolutional neural network (CNN) lacks an inherent mechanism to handle large scale variations, we always need to compute feature maps multiple times for multi-scale object detection, which has the bottleneck of computational cost in practice. To address this, we devise a recurrent scale approximation (RSA) to compute feature map once only, and only through this map can we approximate the rest maps on other levels. At the core of RSA is the recursive rolling out mechanism: given an initial map on a particular scale, it generates the prediction on a smaller scale that is half the size of input. To further increase efficiency and accuracy, we (a): design a scale-forecast network to globally predict potential scales in the image since there is no need to compute maps on all levels of the pyramid. (b): propose a landmark retracing network (LRN) to retrace back locations of the regressed landmarks and generate a confidence score for each landmark; LRN can effectively alleviate false positives due to the accumulated error in RSA. The whole system could be trained end-to-end in a unified CNN framework. Experiments demonstrate that our proposed algorithm is superior against state-of-the-arts on face detection benchmarks and achieves comparable results for generic proposal generation. The source code of RSA is available at github.com/sciencefans/RSA-for-object-detection. …

Wavelet Convolutional Neural Network
Spatial and spectral approaches are two major approaches for image processing tasks such as image classification and object recognition. Among many such algorithms, convolutional neural networks (CNNs) have recently achieved significant performance improvement in many challenging tasks. Since CNNs process images directly in the spatial domain, they are essentially spatial approaches. Given that spatial and spectral approaches are known to have different characteristics, it will be interesting to incorporate a spectral approach into CNNs. We propose a novel CNN architecture, wavelet CNNs, which combines a multiresolution analysis and CNNs into one model. Our insight is that a CNN can be viewed as a limited form of a multiresolution analysis. Based on this insight, we supplement missing parts of the multiresolution analysis via wavelet transform and integrate them as additional components in the entire architecture. Wavelet CNNs allow us to utilize spectral information which is mostly lost in conventional CNNs but useful in most image processing tasks. We evaluate the practical performance of wavelet CNNs on texture classification and image annotation. The experiments show that wavelet CNNs can achieve better accuracy in both tasks than existing models while having significantly fewer parameters than conventional CNNs. …

SEquential Subspace OPtimization (SESOP)
A merger of two optimization frameworks is introduced: SEquential Subspace OPtimization (SESOP) with the MultiGrid (MG) optimization. At each iteration of the combined algorithm, search directions implied by the coarse-grid correction process of MG are added to the low dimensional search-spaces of SESOP, which include the (preconditioned) gradient and search directions involving the previous iterates (so-called history). The resulting accelerated technique is called SESOP-MG. The {\color{black} asymptotic convergence rate} of the two-level version of SESOP-MG (dubbed SESOP-TG) is studied via Fourier mode analysis for linear problems (i.e., optimization of quadratic functionals). Numerical tests on linear and nonlinear {\color{black} problems} demonstrate the effectiveness of the approach. …

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. …

MC-ISTA-Net
The optimization inspired network can bridge convex optimization and neural networks in Compressive Sensing (CS) reconstruction of natural image, like ISTA-Net+, which mapping optimization algorithm: iterative shrinkage-thresholding algorithm (ISTA) into network. However, measurement matrix and input initialization are still hand-crafted, and multi-channel feature map contain information at different frequencies, which is treated equally across channels, hindering the ability of CS reconstruction in optimization-inspired networks. In order to solve the above problems, we proposed MC-ISTA-Net …

Continuous Skip-gram (Skip-gram)
The training objective of the Skip-gram model is to find word representations that are useful for predicting the surrounding words in a sentence or a document. More formally, given a sequence of training words w1,w2,w3, … ,wT , the objective of the Skip-gram model is to maximize the average log probability, where c is the size of the training context (which can be a function of the center word wt). Larger c results in more training examples and thus can lead to a higher accuracy, at the expense of the 2 training time.
http://…/1301.3781.pdf …

RISE Analysis
Described in Bodily, Nyland, and Wiley (2017) <doi:10.19173/irrodl.v18i2.2952>. Automates the process of identifying learning materials that are not effectively supporting student learning in technology-mediated courses by synthesizing information about access to course content and performance on assessments.
The RISE (Resource Inspection, Selection, and Enhancement) Framework is a framework supporting the continuous improvement of open educational resources (OER). The framework is an automated process that identifies learning resources that should be evaluated and either eliminated or improved. This is particularly useful in OER contexts where the copyright permissions of resources allow for remixing, editing, and improving content. The RISE Framework presents a scatterplot with resource usage on the x-axis and grade on the assessments associated with that resource on the y-axis. This scatterplot is broken down into four different quadrants (the mean of each variable being the origin) to find resources that are candidates for improvement. Resources that reside deep within their respective quadrant (farthest from the origin) should be further analyzed for continuous course improvement. We present a case study applying our framework with an Introduction to Business course. Aggregate resource use data was collected from Google Analytics and aggregate assessment data was collected from an online assessment system. Using the RISE Framework, we successfully identified resources, time periods, and modules in the course that should be further evaluated for improvement. …

Multimodal Deep Gaussian Process
We propose a novel Bayesian approach to modelling multimodal data generated by multiple independent processes, simultaneously solving the data association and induced supervised learning problems. Underpinning our approach is the use of Gaussian process priors which encode structure both on the functions and the associations themselves. The association of samples and functions are determined by taking both inputs and outputs into account while also obtaining a posterior belief about the relevance of the global components throughout the input space. We present an efficient learning scheme based on doubly stochastic variational inference and discuss how it can be applied to deep Gaussian process priors. We show results for an artificial data set, a noise separation problem, and a multimodal regression problem based on the cart-pole benchmark. …

REINFORCE
Industrial recommender systems deal with extremely large action spaces — many millions of items to recommend. Moreover, they need to serve billions of users, who are unique at any point in time, making a complex user state space. Luckily, huge quantities of logged implicit feedback (e.g., user clicks, dwell time) are available for learning. Learning from the logged feedback is however subject to biases caused by only observing feedback on recommendations selected by the previous versions of the recommender. In this work, we present a general recipe of addressing such biases in a production top-K recommender system at Youtube, built with a policy-gradient-based algorithm, i.e. REINFORCE. The contributions of the paper are: (1) scaling REINFORCE to a production recommender system with an action space on the orders of millions; (2) applying off-policy correction to address data biases in learning from logged feedback collected from multiple behavior policies; (3) proposing a novel top-K off-policy correction to account for our policy recommending multiple items at a time; (4) showcasing the value of exploration. We demonstrate the efficacy of our approaches through a series of simulations and multiple live experiments on Youtube. …

Shiryaev’s Bayesian Quickest Change Detection (QCD)
This paper provides the first description of a weak practical super-martingale phenomenon that can emerge in the test statistic in Shiryaev’s Bayesian quickest change detection (QCD) problem. We establish that this super-martingale phenomenon can emerge under a condition on the relative entropy between pre and post change densities when the measurements are insufficiently informative to overcome the change time’s geometric prior. We illustrate this super-martingale phenomenon in a simple Bayesian QCD problem which highlights the unsuitability of Shiryaev’s test statistic for detecting subtle change events. …

Graph Spanner
A graph spanner is a fundamental graph structure that faithfully preserves the pairwise distances in the input graph up to a small multiplicative stretch. The common objective in the computation of spanners is to achieve the best-known existential size-stretch trade-off efficiently. Classical models and algorithmic analysis of graph spanners essentially assume that the algorithm can read the input graph, construct the desired spanner, and write the answer to the output tape. However, when considering massive graphs containing millions or even billions of nodes not only the input graph, but also the output spanner might be too large for a single processor to store. …

PriPeARL
Preserving privacy of users is a key requirement of web-scale analytics and reporting applications, and has witnessed a renewed focus in light of recent data breaches and new regulations such as GDPR. We focus on the problem of computing robust, reliable analytics in a privacy-preserving manner, while satisfying product requirements. We present PriPeARL, a framework for privacy-preserving analytics and reporting, inspired by differential privacy. We describe the overall design and architecture, and the key modeling components, focusing on the unique challenges associated with privacy, coverage, utility, and consistency. We perform an experimental study in the context of ads analytics and reporting at LinkedIn, thereby demonstrating the tradeoffs between privacy and utility needs, and the applicability of privacy-preserving mechanisms to real-world data. We also highlight the lessons learned from the production deployment of our system at LinkedIn. …

HierarchicalMeta Learning (HML)
Meta learning is a promising solution to few-shot learning problems. However, existing meta learning methods are restricted to the scenarios where training and application tasks share the same out-put structure. To obtain a meta model applicable to the tasks with new structures, it is required to collect new training data and repeat the time-consuming meta training procedure. This makes them inefficient or even inapplicable in learning to solve heterogeneous few-shot learning tasks. We thus develop a novel and principled HierarchicalMeta Learning (HML) method. Different from existing methods that only focus on optimizing the adaptability of a meta model to similar tasks, HML also explicitly optimizes its generalizability across heterogeneous tasks. To this end, HML first factorizes a set of similar training tasks into heterogeneous ones and trains the meta model over them at two levels to maximize adaptation and generalization performance respectively. The resultant model can then directly generalize to new tasks. Extensive experiments on few-shot classification and regression problems clearly demonstrate the superiority of HML over fine-tuning and state-of-the-art meta learning approaches in terms of generalization across heterogeneous tasks. …

Hierarchical Multiscale LSTM
Hierarchical Multiscale LSTM (Chung et al., 2016a) is a state-of-the-art language model that learns interpretable structure from character-level input. …

Learned Group Signals
We study a model where a data collector obtains data from users through a payment mechanism, aiming to learn the underlying state from the elicited data. The private signal of each user represents her knowledge about the state; and through social interactions each user can also learn noisy versions of her social friends’ signals, which is called `learned group signals’. Thanks to social learning, users have richer information about the state beyond their private signals. Based on both her private signal and learned group signals, each user makes strategic decisions to report a privacy-preserved version of her data to the data collector. We develop a Bayesian game theoretic framework to study the impact of social learning on users’ data reporting strategies and devise the payment mechanism for the data collector accordingly. Our findings reveal that, in general, the desired data reporting strategy at the Bayesian-Nash equilibrium can be in the form of either a symmetric randomized response (SR) strategy or an informative non-disclosive (ND) strategy. Specifically, a generalized majority voting rule is applied by each user to her noisy group signals to determine which strategy to follow. Further, when a user plays the ND strategy, she reports privacy-preserving data completely based on her group signals, independent of her private signal, which indicates that her privacy cost is zero. We emphasize that the reported data when a user plays the ND strategy is still informative about the underlying state because it is based on her learned group signals. As a result, both the data collector and the users can benefit from social learning which drives down the privacy costs and helps to improve the state estimation at a given payment budget. We further derive bounds on the minimum total payment required to achieve a given level of state estimation accuracy. …

Hive Plot
The hive plot is a rational visualization method for drawing networks. Nodes are mapped to and positioned on radially distributed linear axes – this mapping is based on network structural properties. Edges are drawn as curved links. Simple and interpretable. The purpose of the hive plot is to establish a new baseline for visualization of large networks – a method that is both general and tunable and useful as a starting point in visually exploring network structure. …

Lifelong Federated Reinforcement Learning (LFRLA)
This paper was motivated by the problem of how to make robots fuse and transfer their experience so that they can effectively use prior knowledge and quickly adapt to new environments. To address the problem, we present a learning architecture for navigation in cloud robotic systems: Lifelong Federated Reinforcement Learning (LFRLA). In the work, We propose a knowledge fusion algorithm for upgrading a shared model deployed on the cloud. Then, effective transfer learning methods in LFRLA are introduced. LFRLA is consistent with human cognitive science and fits well in cloud robotic systems. Experiments show that LFRLA greatly improves the efficiency of reinforcement learning for robot navigation. The cloud robotic system deployment also shows that LFRLA is capable of fusing prior knowledge. In addition, we release a cloud robotic navigation-learning website based on LFRLA. …

GraphRec
In recent years, Graph Neural Networks (GNNs), which can naturally integrate node information and topological structure, have been demonstrated to be powerful in learning on graph data. These advantages of GNNs provide great potential to advance social recommendation since data in social recommender systems can be represented as user-user social graph and user-item graph; and learning latent factors of users and items is the key. However, building social recommender systems based on GNNs faces challenges. For example, the user-item graph encodes both interactions and their associated opinions; social relations have heterogeneous strengths; users involve in two graphs (e.g., the user-user social graph and the user-item graph). To address the three aforementioned challenges simultaneously, in this paper, we present a novel graph neural network framework (GraphRec) for social recommendations. In particular, we provide a principled approach to jointly capture interactions and opinions in the user-item graph and propose the framework GraphRec, which coherently models two graphs and heterogeneous strengths. Extensive experiments on two real-world datasets demonstrate the effectiveness of the proposed framework GraphRec. …

Hybrid Cosine Based Convolution
Convolutional neural networks (CNNs) have demonstrated their capability to solve different kind of problems in a very huge number of applications. However, CNNs are limited for their computational and storage requirements. These limitations make difficult to implement these kind of neural networks on embedded devices such as mobile phones, smart cameras or advanced driving assistance systems. In this paper, we present a novel layer named Hybrid Cosine Based Convolution that replaces standard convolutional layers using cosine basis to generate filter weights. The proposed layers provide several advantages: faster convergence in training, the receptive field can be increased at no cost and substantially reduce the number of parameters. We evaluate our proposed layers on three competitive classification tasks where our proposed layers can achieve similar (and in some cases better) performances than VGG and ResNet architectures. …

Knowledge Into the Network (KINN)
The promise of ANNs to automatically discover and extract useful features/patterns from data without dwelling on domain expertise although seems highly promising but comes at the cost of high reliance on large amount of accurately labeled data, which is often hard to acquire and formulate especially in time-series domains like anomaly detection, natural disaster management, predictive maintenance and healthcare. As these networks completely rely on data and ignore a very important modality i.e. expert, they are unable to harvest any benefit from the expert knowledge, which in many cases is very useful. In this paper, we try to bridge the gap between these data driven and expert knowledge based systems by introducing a novel framework for incorporating expert knowledge into the network (KINN). Integrating expert knowledge into the network has three key advantages: (a) Reduction in the amount of data needed to train the model, (b) provision of a lower bound on the performance of the resulting classifier by obtaining the best of both worlds, and (c) improved convergence of model parameters (model converges in smaller number of epochs). Although experts are extremely good in solving different tasks, there are some trends and patterns, which are usually hidden only in the data. Therefore, KINN employs a novel residual knowledge incorporation scheme, which can automatically determine the quality of the predictions made by the expert and rectify it accordingly by learning the trends/patterns from data. Specifically, the method tries to use information contained in one modality to complement information missed by the other. We evaluated KINN on a real world traffic flow prediction problem. KINN significantly superseded performance of both the expert and as well as the base network (LSTM in this case) when evaluated in isolation, highlighting its superiority for the task. …

Hierarchical Context Enabled Recurrent Neural Network (HCRNN)
A long user history inevitably reflects the transitions of personal interests over time. The analyses on the user history require the robust sequential model to anticipate the transitions and the decays of user interests. The user history is often modeled by various RNN structures, but the RNN structures in the recommendation system still suffer from the long-term dependency and the interest drifts. To resolve these challenges, we suggest HCRNN with three hierarchical contexts of the global, the local, and the temporary interests. This structure is designed to withhold the global long-term interest of users, to reflect the local sub-sequence interests, and to attend the temporary interests of each transition. Besides, we propose a hierarchical context-based gate structure to incorporate our \textit{interest drift assumption}. As we suggest a new RNN structure, we support HCRNN with a complementary \textit{bi-channel attention} structure to utilize hierarchical context. We experimented the suggested structure on the sequential recommendation tasks with CiteULike, MovieLens, and LastFM, and our model showed the best performances in the sequential recommendations. …

Mixture of Meta-Learners (MxML)
A meta-model is trained on a distribution of similar tasks such that it learns an algorithm that can quickly adapt to a novel task with only a handful of labeled examples. Most of current meta-learning methods assume that the meta-training set consists of relevant tasks sampled from a single distribution. In practice, however, a new task is often out of the task distribution, yielding a performance degradation. One way to tackle this problem is to construct an ensemble of meta-learners such that each meta-learner is trained on different task distribution. In this paper we present a method for constructing a mixture of meta-learners (MxML), where mixing parameters are determined by the weight prediction network (WPN) optimized to improve the few-shot classification performance. Experiments on various datasets demonstrate that MxML significantly outperforms state-of-the-art meta-learners, or their naive ensemble in the case of out-of-distribution as well as in-distribution tasks. …

D-Spectrum
The analysis of dynamics on complex networks is closely connected to structural features of the network itself. Network features like, for instance graph-cores and vertex degrees have been proven to be discriminants of network dynamics and are studied ubiquitously. Here we connect these central discriminants of network dynamics by means of the D-spectrum, a novel framework that identifies a collection of nested chains of subgraphs contained in the network. Cores and vertex degrees can be derived from two particular such chains. Furthermore, each chain gives rise to a rank of a vertex and the collection of these ranks is the D-spectrum of a vertex, providing a novel characterization. We compute this D-spectrum via a node deletion algorithm and we introduce a particular graph dynamical system, called M-C system, in which the D-spectrum appears as a fixed point. Using the D-spectrum we identify nodes of similar spreading power in the susceptible-infectious-recovered (SIR) model on various networks and show that it is more reliable than that based on $k$-core decomposition. In addition we compare the two clusterings obtained by means of vertex infectiousness for different infection probabilities and the D-spectrum and show that they are highly correlated. …

Heterogeneous Transactional Memory (HeTM)
Modern heterogeneous computing architectures, which couple multi-core CPUs with discrete many-core GPUs (or other specialized hardware accelerators), enable unprecedented peak performance and energy efficiency levels. Unfortunately, though, developing applications that can take full advantage of the potential of heterogeneous systems is a notoriously hard task. This work takes a step towards reducing the complexity of programming heterogeneous systems by introducing the abstraction of Heterogeneous Transactional Memory (HeTM). HeTM provides programmers with the illusion of a single memory region, shared among the CPUs and the (discrete) GPU(s) of a heterogeneous system, with support for atomic transactions. Besides introducing the abstract semantics and programming model of HeTM, we present the design and evaluation of a concrete implementation of the proposed abstraction, which we named Speculative HeTM (SHeTM). SHeTM makes use of a novel design that leverages on speculative techniques and aims at hiding the inherently large communication latency between CPUs and discrete GPUs and at minimizing inter-device synchronization overhead. SHeTM is based on a modular and extensible design that allows for easily integrating alternative TM implementations on the CPU’s and GPU’s sides, which allows the flexibility to adopt, on either side, the TM implementation (e.g., in hardware or software) that best fits the applications’ workload and the architectural characteristics of the processing unit. We demonstrate the efficiency of the SHeTM via an extensive quantitative study based both on synthetic benchmarks and on a porting of a popular object caching system. …

Temporal-Difference Learning (TD Learning)
Temporal Difference (TD) learning refers to a class of model-free reinforcement learning methods which learn by bootstrapping from the current estimate of the value function. These methods sample from the environment, like Monte Carlo methods, and perform updates based on current estimates, like dynamic programming methods. While Monte Carlo methods only adjust their estimates once the final outcome is known, TD methods adjust predictions to match later, more accurate, predictions about the future before the final outcome is known. This is a form of bootstrapping, as illustrated with the following example: ‘Suppose you wish to predict the weather for Saturday, and you have some model that predicts Saturday’s weather, given the weather of each day in the week. In the standard case, you would wait until Saturday and then adjust all your models. However, when it is, for example, Friday, you should have a pretty good idea of what the weather would be on Saturday – and thus be able to change, say, Saturday’s model before Saturday arrives’. Temporal difference methods are related to the temporal difference model of animal learning.
Temporal Difference Learning in Python
Temporal Difference Learning with Neural Networks – Study of the Leakage Propagation Problem …

Automated Planning and Scheduling
Automated planning and scheduling, sometimes denoted as simply AI Planning, is a branch of artificial intelligence that concerns the realization of strategies or action sequences, typically for execution by intelligent agents, autonomous robots and unmanned vehicles. Unlike classical control and classification problems, the solutions are complex and must be discovered and optimized in multidimensional space. Planning is also related to decision theory. In known environments with available models, planning can be done offline. Solutions can be found and evaluated prior to execution. In dynamically unknown environments, the strategy often needs to be revised online. Models and policies must be adapted. Solutions usually resort to iterative trial and error processes commonly seen in artificial intelligence. These include dynamic programming, reinforcement learning and combinatorial optimization. Languages used to describe planning and scheduling are often called action languages. …

BlackOut
We propose BlackOut, an approximation algorithm to efficiently train massive recurrent neural network language models (RNNLMs) with million word vocabularies. BlackOut is motivated by using a discriminative loss, and we describe a new sampling strategy which significantly reduces computation while improving stability, sample efficiency, and rate of convergence. One way to understand BlackOut is to view it as an extension of the DropOut strategy to the output layer, wherein we use a discriminative training loss and a weighted sampling scheme. We also establish close connections between BlackOut, importance sampling, and noise contrastive estimation (NCE). Our experiments, on the recently released one billion word language modeling benchmark, demonstrate scalability and accuracy of BlackOut; we outperform the state-of-the art, and achieve the lowest perplexity scores on this dataset. Moreover, unlike other established methods which typically require GPUs or CPU clusters, we show that a carefully implemented version of BlackOut requires only 1-10 days on a single machine to train a RNNLM with a million word vocabulary and billions of parameters on one billion of words. …

MetaGrasp
Data-driven approach for grasping shows significant advance recently. But these approaches usually require much training data. To increase the efficiency of grasping data collection, this paper presents a novel grasp training system including the whole pipeline from data collection to model inference. The system can collect effective grasp sample with a corrective strategy assisted by antipodal grasp rule, and we design an affordance interpreter network to predict pixelwise grasp affordance map. We define graspability, ungraspability and background as grasp affordances. The key advantage of our system is that the pixel-level affordance interpreter network trained with only a small number of grasp samples under antipodal rule can achieve significant performance on totally unseen objects and backgrounds. The training sample is only collected in simulation. Extensive qualitative and quantitative experiments demonstrate the accuracy and robustness of our proposed approach. In the real-world grasp experiments, we achieve a grasp success rate of 93% on a set of household items and 91% on a set of adversarial items with only about 6,300 simulated samples. We also achieve 87% accuracy in clutter scenario. Although the model is trained using only RGB image, when changing the background textures, it also performs well and can achieve even 94% accuracy on the set of adversarial objects, which outperforms current state-of-the-art methods. …

Deep Variational Canonical Correlation Analysis (VCCA)
We present deep variational canonical correlation analysis (VCCA), a deep multi-view learning model that extends the latent variable model interpretation of linear CCA~\citep{BachJordan05a} to nonlinear observation models parameterized by deep neural networks (DNNs). Marginal data likelihood as well as inference are intractable under this model. We derive a variational lower bound of the data likelihood by parameterizing the posterior density of the latent variables with another DNN, and approximate the lower bound via Monte Carlo sampling. Interestingly, the resulting model resembles that of multi-view autoencoders~\citep{Ngiam_11b}, with the key distinction of an additional sampling procedure at the bottleneck layer. We also propose a variant of VCCA called VCCA-private which can, in addition to the ‘common variables’ underlying both views, extract the ‘private variables’ within each view. We demonstrate that VCCA-private is able to disentangle the shared and private information for multi-view data without hard supervision. …

Efficient Alternating Direction Multiplier Method (ADMM)
Feature selection can efficiently identify the most informative features with respect to the target feature used in training. However, state-of-the-art vector-based methods are unable to encapsulate the relationships between feature samples into the feature selection process, thus leading to significant information loss. To address this problem, we propose a new graph-based structurally interacting elastic net method for feature selection. Specifically, we commence by constructing feature graphs that can incorporate pairwise relationship between samples. With the feature graphs to hand, we propose a new information theoretic criterion to measure the joint relevance of different pairwise feature combinations with respect to the target feature graph representation. This measure is used to obtain a structural interaction matrix where the elements represent the proposed information theoretic measure between feature pairs. We then formulate a new optimization model through the combination of the structural interaction matrix and an elastic net regression model for the feature subset selection problem. This allows us to a) preserve the information of the original vectorial space, b) remedy the information loss of the original feature space caused by using graph representation, and c) promote a sparse solution and also encourage correlated features to be selected. Because the proposed optimization problem is non-convex, we develop an efficient alternating direction multiplier method (ADMM) to locate the optimal solutions. Extensive experiments on various datasets demonstrate the effectiveness of the proposed methods. …

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. …

TF-Replicator
We describe TF-Replicator, a framework for distributed machine learning designed for DeepMind researchers and implemented as an abstraction over TensorFlow. TF-Replicator simplifies writing data-parallel and model-parallel research code. The same models can be effortlessly deployed to different cluster architectures (i.e. one or many machines containing CPUs, GPUs or TPU accelerators) using synchronous or asynchronous training regimes. To demonstrate the generality and scalability of TF-Replicator, we implement and benchmark three very different models: (1) A ResNet-50 for ImageNet classification, (2) a SN-GAN for class-conditional ImageNet image generation, and (3) a D4PG reinforcement learning agent for continuous control. Our results show strong scalability performance without demanding any distributed systems expertise of the user. The TF-Replicator programming model will be open-sourced as part of TensorFlow 2.0 (see https://…/25 ). …