标题：Beyond Symmetric Clusters: Finding Inter-Cluster Structures in Graphs

报告时间：2024年3月18日（星期一）9:30-11:00

报告地点：净月大街校区信息科学与技术学院楼324会议室

主讲人：He Sun

主办单位：信息科学与技术学院

报告内容简介：

　　Graph clustering is a fundamental problem in unsupervised learning, with comprehensive applications in computer science and related fields. In many real-world applications, we find that the clusters have a significant high-level structure. This is often overlooked in the design and analysis of graph clustering algorithms which make strong simplifying assumptions about the structure of the graph.  

　　In this talk I will address the natural question of whether the structure of clusters can be learned efficiently, present new algorithms for learning the inter-cluster structure of graphs in both centralised and local settings, and discuss their applications in analysing real-world datasets.  

　　This is based on joint work with Peter Macgregor (University of Edinburgh).

主讲人简介：

　　He Sun is a Reader of Algorithms and Complexity in the School of Informatics, University of Edinburgh. He received his PhD from Fudan University, and worked at the Max Planck Institute for Informatics, UC Berkeley, and University of Bristol, before joining the University of Edinburgh in 2017.  

　　He received the President's Medal of Fudan University (2004), Shanghai Outstanding PhD Thesis Award (2010), and Simons-Berkeley Research Fellowship (2014). In 2020, he received a prestigious EPSRC Fellowship of 1.51 million pounds for developing advanced spectral algorithms and their open-source implementation. In 2023, he was invited to work at the Simons Institute for the Theory of Computing, UC Berkeley.

　　He has been invited to work in the program committees of several international conferences, and he is currently serving as an Area Chair of ICML 2024.