时 间：2023年3月23日 10:30-11:30
地 点：腾讯会议：860-464-066
报告人：刘奕鑫 博士 澳大利亚莫纳什大学
主持人：谌自奇 研究员 华东师范大学
摘 要：
In recent years, graph neural networks have drawn much attention in both academic and industrial communities. Following the prevailing (semi-) supervised learning paradigms, most graph neural networks suffer from several shortcomings, including heavy label reliance, poor generalization, and weak robustness. To circumvent these issues, graph self-supervised learning (GSSL), which extracts supervision signals for model training with well-designed pretext tasks instead of manual labels, has become a promising and trending learning paradigm for graph data. In this talk, I will introduce the development of graph neural networks and provide a global perspective on the development of GSSL. After that, I will introduce our recent works on the methodology and applications of GSSL on the topics of graph representation learning, anomaly detection, and graph structure learning.
报告人简介：
Yixin Liu is a third-year Ph.D. student at Monash University, supervised by Prof. Shirui Pan. His research mainly focuses on graph representation learning and graph neural networks, with an emphasis on self-supervised and weak-supervised scenarios. Previously, he obtained B.Sc and M.Sc from Beihang University in 2017 and 2020, respectively. He received the Google Ph.D. Fellowship award in 2022. He published several papers in top-tier conferences and journals including AAAI, WWW, WSDM, CIKM, TNNLS, and TKDE. He served as the PC member/reviewer of the following major AI/ML conferences including SIGKDD, AAAI, IJCAI, ICDM, TKDE, TNNLS, TIP, etc.