报告主题： Motif-based bipartite graph learning: a topological perspective

报 告 人：喻坚

报告时间：2025年10月27日（周一） 9:00-15:00

报告地点：计算机大楼A505

报告摘要：

 In this talk, we first examine the graph as a discrete structure from an algebraic topology perspective and put graphs into the context of simplicial complexes and chain complexes. We then connect the matrices used to encode graphs, including incidence matrix, adjacency matrix, and graph Laplacian matrix, to concepts of gradient, divergence, and the boundary and co-boundary operators in chain complexes. Based on that, we examine the function of the popular GCN (Graph Convolutional neural network) layer and relate it to the heat diffusion differential equation. finally, we introduce our recent works on graph motifs based bipartite graph link prediction and its application in recommender systems.

报告人简介：

  Dr Jian Yu (喻坚) is an Associate Professor in the Department of Computer Science, Auckland University of Technology. He is currently the director of the Ubiquitous and Web Computing Research Lab (Ubiweb) in the Department of Computer Science and Software Engineering, ECMS. His current research interests include deep learning for recommender systems, graph neural networks, complex networks, Web and ubiquitous computing, and service-oriented computing. He has served as PC Member for over 100 international conferences including CORE Rank A conferences ACM CIKM, ICSOC, IEEE SCC, EAI MobiQuitous, COOPIS, and IEEE TrustCom. Dr Yu has over 140 publications and has published in top journals such as ACM Computing Surveys (IF 14.32), IEEE Trans. Services Computing (IF 11.019), IEEE Trans. Intelligent Transport Systems (IF 9.551), IEEE Internet of Things Journal (IF 10.238), Elsevier Future Generation Computer Systems (IF 7.307), Knowledge-Based Systems (IF 8.139) and Expert Systems with Applications (IF 8.665).  He is Associate Editor for Springer Journal of Reliable and Intelligent Environments and has organized several special issues for journals including Oxford The Computer Journal, Elsevier JCSS, and Springer Computing, and has organized over ten international conferences and workshops.