报告主题：Graph Embedding and Recommendation for Big Graph Data

报 告 人：喻坚

报告时间：2024年4月26日 19:00-21:00

报告地点：计算机大楼A505

报告摘要：

Graphs are a fundamental tool for understanding and modelling complex systems in physics, biology, neuroscience, engineering, and social science. Graph embedding, which is the way to encode graph structure in the Euclidean space so that it can be easily exploited by machine learning tasks, is a primary challenge in machine learning on graphs. This talk first introduces the concept of graph and its matrix representations such as Graph Laplacian, then presents three mainstream graph embedding methods including matrix-factorization based, random-walk based, and deep-neural-network based methods. We also present our approach in utilizing graph embedding for Motif-Aware Web-API recommendation.

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.