Graph Convolution Networks (GCN) are widely used in learning graph representations due to their effectiveness and efficiency. However, they suffer from the notorious over-smoothing problem, in which the learned representations of densely connected nodes converge to alike vectors when many (>3) graph convolutional layers are stacked. In this paper, we argue that there-normalization trick used in GCN leads to overly homogeneous information propagation, which is the source of over-smoothing. To address this problem, we propose Graph Highway Networks(GHNet) which utilize gating units to automatically balance the trade-off between homogeneity and heterogeneity in the GCN learning process. The gating units serve as direct highways to maintain heterogeneous information from the node itself after feature propagation. This design enables GHNet to achieve much larger receptive fields per node without over-smoothing and thus access to more of the graph connectivity information. Experimental results on benchmark datasets demonstrate the superior performance of GHNet over GCN and related models.

Location is key to spatialize internet-of-things (IoT) data. However, it is challenging to use low-cost IoT devices for robust unsupervised localization (i.e., localization without training data that have known location labels). Thus, this paper proposes a deep reinforcement learning (DRL) based unsupervised wireless-localization method. The main contributions are as follows. (1) This paper proposes an approach to model a continuous wireless-localization process as a Markov decision process (MDP) and process it within a DRL framework. (2) To alleviate the challenge of obtaining rewards when using unlabeled data (e.g., daily-life crowdsourced data), this paper presents a reward-setting mechanism, which extracts robust landmark data from unlabeled wireless received signal strengths (RSS). (3) To ease requirements for model re-training when using DRL for localization, this paper uses RSS measurements together with agent location to construct DRL inputs. The proposed method was tested by using field testing data from multiple Bluetooth 5 smart ear tags in a pasture. Meanwhile, the experimental verification process reflected the advantages and challenges for using DRL in wireless localization.

This paper builds on recent developments in Bayesian network (BN) structure learning under the controversial assumption that the input variables are dependent. This assumption is geared towards real-world datasets that incorporate variables which are assumed to be dependent. It aims to address the problem of learning multiple disjoint subgraphs which do not enable full propagation of evidence. A novel hybrid structure learning algorithm is presented in this paper for this purpose, called SaiyanH. The results show that the algorithm discovers satisfactorily accurate connected DAGs in cases where all other algorithms produce multiple disjoint subgraphs for dependent variables. This problem is highly prevalent in cases where the sample size of the input data is low with respect to the dimensionality of the model, which is often the case when working with real data. Based on six case studies, five different sample sizes, three different evaluation metrics, and other state-of-the-art or well-established constraint-based, score-based and hybrid learning algorithms, the results rank SaiyanH 4th out of 13 algorithms for overall performance.

With the spiraling pandemic of the Coronavirus Disease 2019 (COVID-19), it has becoming inherently important to disseminate accurate and timely information about the disease. Due to the ubiquity of Internet connectivity and smart devices, social sensing is emerging as a dynamic sensing paradigm to collect real-time observations from online users. In this vision paper we propose CovidSens, the concept of social-sensing-based risk alerting systems to notify the general public about the COVID-19 spread. The CovidSens concept is motivated by two recent observations: 1) people have been actively sharing their state of health and experience of the COVID-19 via online social media, and 2) official warning channels and news agencies are relatively slower than people reporting their observations and experiences about COVID-19 on social media. We anticipate an unprecedented opportunity to leverage the posts generated by the social media users to build a real-time analytic system for gathering and circulating vital information of the COVID-19 propagation. Specifically, the vision of CovidSens attempts to answer the questions of: how to track the spread of the COVID-19? How to distill reliable information about the disease with the coexistence of prevailing rumors and misinformation in the social media? How to inform the general public about the latest state of the spread timely and effectively and alert them to remain prepared? In this vision paper, we discuss the roles of CovidSens and identify the potential challenges in implementing reliable social-sensing-based risk alerting systems. We envision that approaches originating from multiple disciplines (e.g. estimation theory, machine learning, constrained optimization) can be effective in addressing the challenges. Finally, we outline a few research directions for future work in CovidSens.

In most real-world applications, it is seldom the case that a given observable evolves independently of its environment. In social networks, users' behavior results from the people they interact with, news in their feed, or trending topics. In natural language, the meaning of phrases emerges from the combination of words. In general medicine, a diagnosis is established on the basis of the interaction of symptoms. Here, we propose a new model, the Interactive Mixed Membership Stochastic Block Model (IMMSBM), which investigates the role of interactions between entities (hashtags, words, memes, etc.) and quantifies their importance within the aforementioned corpora. We find that interactions play an important role in those corpora. In inference tasks, taking them into account leads to average relative changes with respect to non-interactive models of up to 150\% in the probability of an outcome. Furthermore, their role greatly improves the predictive power of the model. Our findings suggest that neglecting interactions when modeling real-world phenomena might lead to incorrect conclusions being drawn.

Deep learning algorithms can be seen as compositions of functions acting on learned representations encoded as tensor-structured data. However, in most applications those representations are monolithic, with for instance one single vector encoding an entire image or sentence. In this paper, we build upon the recent successes of Graph Neural Networks (GNNs) to explore the use of graph-structured representations for learning spatial configurations. Motivated by the ability of humans to distinguish arrangements of shapes, we introduce two novel geometrical reasoning tasks, for which we provide the datasets. We introduce novel GNN layers and architectures to solve the tasks and show that graph-structured representations are necessary for good performance.

This paper studies the large-scale subspace clustering (LSSC) problem with million data points. Many popular subspace clustering methods cannot directly handle the LSSC problem although they have been considered as state-of-the-art methods for small-scale data points. A basic reason is that these methods often choose all data points as a big dictionary to build huge coding models, which results in a high time and space complexity. In this paper, we develop a learnable subspace clustering paradigm to efficiently solve the LSSC problem. The key idea is to learn a parametric function to partition the high-dimensional subspaces into their underlying low-dimensional subspaces instead of the expensive costs of the classical coding models. Moreover, we propose a unified robust predictive coding machine (RPCM) to learn the parametric function, which can be solved by an alternating minimization algorithm. In addition, we provide a bounded contraction analysis of the parametric function. To the best of our knowledge, this paper is the first work to efficiently cluster millions of data points among the subspace clustering methods. Experiments on million-scale datasets verify that our paradigm outperforms the related state-of-the-art methods in both efficiency and effectiveness.

Constructing approximations that can accurately mimic the behaviour of complex models at reduced computational costs is an important aspect of uncertainty quantification. Despite their flexibility and efficiency, classical surrogate models such as Kriging or polynomial chaos expansions tend to struggle with highly non-linear, localized or non-stationary computational models. We hereby propose a novel sequential adaptive surrogate modelling method based on recursively embedding locally spectral expansions. It is achieved by means of disjoint recursive partitioning of the input domain, which consists in sequentially splitting the latter into smaller subdomains, and constructing a simpler local spectral expansions in each, exploiting the trade-off complexity vs. locality. The resulting expansion, which we refer to as "stochastic spectral embedding" (SSE), is a piece-wise continuous approximation of the model response that shows promising approximation capabilities, and good scaling with both the problem dimension and the size of the training set. We finally show how the method compares favourably against state-of-the-art sparse polynomial chaos expansions on a set of models with different complexity and input dimension.

Anomaly localization is an essential problem as anomaly detection is. Because a rigorous localization requires a causal model of a target system, practically we often resort to a relaxed problem of anomaly interpretation, for which we are to obtain meaningful attribution of anomaly scores to input features. In this paper, we investigate the use of the Shapley value for anomaly interpretation. We focus on the semi-supervised anomaly detection and newly propose a characteristic function, on which the Shapley value is computed, specifically for anomaly scores. The idea of the proposed method is approximating the absence of some features by minimizing an anomaly score with regard to them. We examine the performance of the proposed method as well as other general approaches to computing the Shapley value in interpreting anomaly scores. We show the results of experiments on multiple datasets and anomaly detection methods, which indicate the usefulness of the Shapley-based anomaly interpretation toward anomaly localization.

In this paper, we propose a dimensionality reduction method applied to tensor-structured data as a hidden layer (we call it TensorProjection Layer) in a convolutional neural network. Our proposed method transforms input tensors into ones with a smaller dimension by projection. The directions of projection are viewed as training parameters associated with our proposed layer and trained via a supervised learning criterion such as minimization of the cross-entropy loss function. We discuss the gradients of the loss function with respect to the parameters associated with our proposed layer. We also implement simple numerical experiments to evaluate the performance of the TensorProjection Layer.