Reporting time: July 17, 2021 10:00-11:00

Report location: Room 406, Feiyun Building, Lanzhou University

Speaker: Qidong Liu Moderator: Jizhao Liu

Speaker profile: Qidong Liu, male, master's supervisor; graduated from Lanzhou University (School of Information Science and Engineering) in December 2018 with a doctorate degree in engineering; 2019-2021, engaged in post-doctoral research at Nanyang Technological University (School of Electrical and Electronic Engineering) in Singapore; now associate professor (direct hire) of the School of Information Engineering, Zhengzhou University. The main research directions include recommendation systems, complex networks, swarm intelligence, spatiotemporal data analysis, and graph neural networks. Currently, he is in charge of 1 National Natural Science Foundation of China and 1 general project of China Postdoctoral Fund. He has published more than 10 papers in internationally renowned journals and conferences, and has served as a reviewer for many important domestic and foreign journals and conferences, including IEEE T-CYB, KBS, AAAI, etc.

Report summary: Graph Neural Networks (GNN) is a hot topic in the field of deep learning, especially since the introduction of Graph Convolutional Networks (GCN), deep learning has the potential to realize causal reasoning. GNN's outstanding ability to process unstructured data has made new breakthroughs in network data analysis, recommendation systems, physical modeling, natural language processing, and combined optimization problems on graphs. This report will track the cutting-edge progress in related fields, discuss the latest papers, and nurture research ideas.