The community detection problem involves making inferences about node labels in a graph based on observing the graph edges. Applications include recommendation systems, advertisement in social networks, and fraud detection. Motivated by the natural presence of non-graphical data along with graphical observations in many practical inference problems, we investigate the influence of non-graphical side information on community detection via analyzing the inference phase transition threshold. For the two-community problem, the effect of partially revealed labels and noisy label side information is discussed. A more general side information with arbitrary alphabet consisting of k features is studied. In the second part of this talk, we extend the method of Extrinsic Information Transfer (EXIT) from the field of iterative decoding to the analysis of belief propagation in the community detection problem. We show that new insights are obtained by this transposition that were not available otherwise. Applications and implications of these results will be discussed.
Aria Nosratinia is Erik Jonsson Distinguished Professor and associate head of the Electrical Engineering Department at the University of Texas at Dallas. He received his Ph.D. in Electrical and Computer Engineering from the University of Illinois at Urbana-Champaign in 1996. He has held visiting appointments at Princeton University, Rice University, and UCLA. His interests lie in the broad area of information theory and signal processing, with applications in wireless communication. Dr. Nosratinia is a fellow of IEEE for contributions to multimedia and wireless communications. He has served as editor and area editor for the IEEE Transactions on Wireless Communications, and editor for the IEEE Transactions on Information Theory, IEEE Transactions on Image Processing, IEEE Signal Processing Letters, IEEE Wireless Communications, and Journal of Circuits, Systems, and Computers. He has received the National Science Foundation career award, and the outstanding service award from the IEEE Signal Processing Society, Dallas Chapter. He has served on the organizing committees and technical program committees for a number of conferences, most recently as the general co-chair of ITW 2018. He was named a highly cited researcher by Clarivate Analytics (formerly Thomson Reuters).