Graph, as a very expressive model, has been widely used to model real-world entities and their relationships in application-specific networks, e.g., social networks, road networks, biological networks, communication networks, etc. The ubiquity of such networks, the ever-increasing size, the dynamic nature, and the rich semantics have brought us a lot of research opportunities as well as new challenges. We need in-depth, efficient and scalable mining and analysis tools to discover the hidden knowledge from these massive and complex networks and further enhance our understanding. In this talk, I shall discuss the recent development of machine learning on graph structure data and its applications. I shall pay special attention to the robustness and interpretability of graph learning.

Jia Li is a Ph.D. student in Department of Systems Engineering and Engineering Management at The Chinese University of Hong Kong since 2017. His research mainly lies in the areas of machine learning and data mining, with a focus on developing models that analyze graph data. He worked as a full-time data mining engineer in Tencent from 2014 to 2017, in which he was responsible for risk management and fraud prevention for WeChat Pay. Before that, he got M.S. degree in Computer Science at The Chinese University of Hong Kong. He has published several papers on data mining, machine learning top conferences KDD, WWW, NeurIPS.