Learning representations of large-scale networks

Information networks (e.g., social networks, citation networks, and World Wide Web ) are ubiquitous in real world, covering a variety of applications. Traditionally, networks are usually represented as adjacency matrices. However, this type of representation is very sparse and high-dimensional, which does not facilitate computation of network analysis and network understanding. In this talk, Dr. Tang will introduce his recent work on learning low-dimensional representations of large-scale networks. The representations are able to facility a variety of applications such as node classification, link prediction and network visualization. He will also introduce his future plans along this direction.
Dr. Jian Tang is currently a postdoctoral research fellow in University of Michigan. He received his Ph.D degree from Peking University and was a researcher in Microsoft Research Asia. His current research interests are deep learning, reinforcement learning, statistical topic modelling with applications in natural language understanding, information network analysis, data visualization, and information retrieval. His major research work are published in prestigious machine learning and data mining conferences including ICML, KDD, WWW, AAAI. He received the best paper award of ICML'14 and best paper nomination of WWW'16. He is a PC member of many prestigious conferences including IJCAI, AAAI, ACL, EMNLP, WWW, KDD etc.