Speaker: Prof. Huawei Shen
(Professor, Chinese Academy of Sciences, China)
Graph Convolutional Neural Networks
Convolutional neural networks (CNNs) have been successfully used in many machine learning problems, such as image classification and speech recognition, where there is an underlying Euclidean structure. One interesting research problem is how to generalize convolutional neural network to non-Euclidean data, for example, graph data. This talk will introduce the research progress on this direction, i.e., graph convolutional neural networks and their applications on some tasks, e.g., node classification, link prediction, graph classification.
Dr. Huawei Shen is a Professor at the Institute of Computing Technology, Chinese Academy of Sciences. He earned his Ph.D. degree from the University of Chinese Academy of Sciences in 2010. His research interests include social media analytics, web data mining, and deep learning on graph. He has published over 100 research papers in referred international journals, including PNAS, IEEE TKDE, Physical Review E, and conference proceedings, including WWW, SIGIR, AAAI, IJCAI, and CIKM. He regularly serves on the Program Committee for premier conferences like KDD, WWW, SIGIR, AAAI, IJCAI, CIKM, ICWSM etc.
Speaker: Prof. Xiangliang Zhang
(Associate Professor, KAUST, Saudi Arabia)
The Dynamics, Uncertainty and Heterogeneity in Network Embedding
Network embedding has been playing important roles in diverse network management and analysis applications. Social networks face challenges of the dynamics in network structure evolution, the uncertainty in social activities and the heterogeneity of node attributes. This talk will discuss the impact of these difficulties on network embedding, and introduce recent solutions to them based on variational autoencoder for encoding the uncertainty, Kalman Filter for learning the dynamic transition of node embeddings, and biased random walks for resolving the node heterogeneity. The obtained embedding results will be demonstrated in standard applications of node classification and link prediction, as well as dynamic user profiling and scholars’ research interest characterization.
Dr. Xiangliang Zhang is an Associate Professor of Computer Science and directs the Machine Intelligence and kNowledge Engineering (MINE) group at KAUST, Saudi Arabia. She earned her Ph.D. degree in computer science from INRIA-Universite Paris-Sud, France, in July 2010. She received M.S. and B.S. degrees from Xi’an Jiaotong University, China, in 2006 and 2003, respectively. Dr. Zhang's research mainly focuses on learning from complex and large-scale streaming and graph data. Dr. Zhang has published over 100 research papers in referred international journals and conference proceedings, including TKDE, SIGKDD, AAAI, IJCAI, ICDM, VLDB J, ICDE etc. She is the associated editor of Information Sciences and Health Information Science and Systems. She regularly serves on the Program Committee for premier conferences like SIGKDD, AAAI (Senior PC), IJCAI (Senior PC), ICDM, NIPS, ICML etc. Dr. Zhang is selected and invited to deliver an Early Career Spotlight talk at IJCAI-ECAI 2018.