JGraphT
Mathematical software and graph-theoretical algorithmic packages to efficiently model, analyze and query graphs are crucial in an era where large-scale spatial, societal and economic network data are abundantly available. One such package is JGraphT, a programming library which contains very efficient and generic graph data-structures along with a large collection of state-of-the-art algorithms. The library is written in Java with stability, interoperability and performance in mind. A distinctive feature of this library is the ability to model vertices and edges as arbitrary objects, thereby permitting natural representations of many common networks including transportation, social and biological networks. Besides classic graph algorithms such as shortest-paths and spanning-tree algorithms, the library contains numerous advanced algorithms: graph and subgraph isomorphism; matching and flow problems; approximation algorithms for NP-hard problems such as independent set and TSP; and several more exotic algorithms such as Berge graph detection. Due to its versatility and generic design, JGraphT is currently used in large-scale commercial, non-commercial and academic research projects. In this work we describe in detail the design and underlying structure of the library, and discuss its most important features and algorithms. A computational study is conducted to evaluate the performance of JGraphT versus a number of similar libraries. Experiments on a large number of graphs over a variety of popular algorithms show that JGraphT is highly competitive with other established libraries such as NetworkX or the BGL. …

Sparse Deep Predictive Coding (SDPC)
Convolutional Neural Networks (CNNs) are the state-of-the-art algorithms used in computer vision. However, these models often suffer from the lack of interpretability of their information transformation process. To address this problem, we introduce a novel model called Sparse Deep Predictive Coding (SDPC). In a biologically realistic manner, SDPC mimics how the brain is efficiently representing visual information. This model complements the hierarchical convolutional layers found in CNNs with the feed-forward and feed-back update scheme described in the Predictive Coding (PC) theory and found in the architecture of the mammalian visual system. We experimentally demonstrate on two databases that the SDPC model extracts qualitatively meaningful features. These features, besides being similar to some of the biological Receptive Fields of the visual cortex, also represent hierarchically independent components of the image that are crucial to describe it in a generic manner. For the first time, the SDPC model demonstrates a meaningful representation of features within the hierarchical generative model and of the decision-making process leading to a specific prediction. A quantitative analysis reveals that the features extracted by the SDPC model encode the input image into a representation that is both easily classifiable and robust to noise. …

Teacher-Student Feature Selection (TSFS)
High-dimensional data in many machine learning applications leads to computational and analytical complexities. Feature selection provides an effective way for solving these problems by removing irrelevant and redundant features, thus reducing model complexity and improving accuracy and generalization capability of the model. In this paper, we present a novel teacher-student feature selection (TSFS) method in which a ‘teacher’ (a deep neural network or a complicated dimension reduction method) is first employed to learn the best representation of data in low dimension. Then a ‘student’ network (a simple neural network) is used to perform feature selection by minimizing the reconstruction error of low dimensional representation. Although the teacher-student scheme is not new, to the best of our knowledge, it is the first time that this scheme is employed for feature selection. The proposed TSFS can be used for both supervised and unsupervised feature selection. This method is evaluated on different datasets and is compared with state-of-the-art existing feature selection methods. The results show that TSFS performs better in terms of classification and clustering accuracies and reconstruction error. Moreover, experimental evaluations demonstrate a low degree of sensitivity to parameter selection in the proposed method. …

Self-Supervised Spectral Graph Representation Learning (SGR)
Representing a graph as a vector is a challenging task; ideally, the representation should be easily computable and conducive to efficient comparisons among graphs, tailored to the particular data and analytical task at hand. Unfortunately, a ‘one-size-fits-all’ solution is unattainable, as different analytical tasks may require different attention to global or local graph features. We develop SGR, the first, to our knowledge, method for learning graph representations in a self-supervised manner. Grounded on spectral graph analysis, SGR seamlessly combines all aforementioned desirable properties. In extensive experiments, we show how our approach works on large graph collections, facilitates self-supervised representation learning across a variety of application domains, and performs competitively to state-of-the-art methods without re-training. …