IEEE Transactions on Signal and Information Processing over Networks

Novel Monte Carlo estimators are proposed to solve both the Tikhonov regularization (TR) and the interpolation problems on graphs. These estimators are based on random spanning forests (RSF), the theoretical properties of which enable to analyze the estimators’ theoretical mean and variance.

In this paper, we investigate the resource allocation problem for a full-duplex (FD) massive multiple-input-multiple-output (mMIMO) multi-carrier (MC) decode and forward (DF) relay system which serves multiple MC single-antenna half-duplex (HD) nodes. In addition to the prior studies focusing on maximizing the sum-rate and energy efficiency, we focus on minimizing the overall delivery time for a given set of communication tasks to the user terminals.

The problem of graph learning concerns the construction of an explicit topological structure revealing the relationship between nodes representing data entities, which plays an increasingly important role in the success of many graph-based representations and algorithms in the field of machine learning and graph signal processing.

As a fundamental algorithm for collaborative processing over multi-agent systems, distributed consensus algorithm has been studied for optimizing its convergence rate. Due to the close analogy between the diffusion problem and the consensus algorithm, the previous trend in the literature is to transform the diffusion system from the spatially continuous domain into the spatially discrete one. 

Graph neural networks have emerged as a popular and powerful tool for learning hierarchical representation of graph data. In complement to graph convolution operators, graph pooling is crucial for extracting hierarchical representation of data in graph neural networks. However, most recent graph pooling methods still fail to efficiently exploit the geometry of graph data. In this paper, we propose a novel graph pooling strategy that leverages node affinity to improve the hierarchical representation learning of graph data. 

In order to perform network analysis tasks, representations that capture the most relevant information in the graph structure are needed. However, existing methods learn representations that cannot be interpreted in a straightforward way and that are relatively unstable to perturbations of the graph structure. We address these two limitations by proposing node2coords, a representation learning algorithm for graphs, which learns simultaneously a low-dimensional space and coordinates for the nodes in that space.

Decentralized detection is one of the key tasks that a wireless sensor network (WSN) is faced to accomplish. Among several decision criteria, the Rao test is able to cope with an unknown (but parametrically-specified) sensing model, while keeping computational simplicity. To this end, the Rao test is employed in this paper to fuse multivariate data measured by a set of sensor nodes, each observing the target (or the desired) event via a nonlinear mapping function. 

Combining diffusion strategies with complementary properties enables enhanced performance when they can be run simultaneously. In this article, we first propose two schemes for the convex combination of two diffusion strategies, namely, the power-normalized scheme and the sign-regressor scheme. Then, we conduct theoretical analysis for one of the schemes, i.e., the power-normalized one.

Graph distance (or similarity) scores are used in several graph mining tasks, including anomaly detection, nearest neighbor and similarity search, pattern recognition, transfer learning, and clustering. Graph distances that are metrics and, in particular, satisfy the triangle inequality, have theoretical and empirical advantages. 

Control over noisy communication-channels” invented by Sahai-Mitter-and-Tatikonda is a prominent topic. In this context, the latency-and-reliability trade-off is considered by responding to the following: How much fast? How much secure? For a stochastic-mean-field-game (S-MFG), we assign the source-codes as the agents. Additionally, the total-Reward is the Volume of the maximum secure lossy source-coding-rate achievable between a set of Sensors, and the Fusion-Centre (FC) set – including intercepting-Byzantines.