学术报告|UCLA副教授孙怡舟博士

报告题目

Neural Operators for Graph-Level Proximity Computation and Representation Learning

报告时间

2019年06月21日（周五）下午14:00-16:00

报告地点

北京大学理科二号楼 2736

主讲人

孙怡舟博士

Yizhou Sun, Ph.D.

Associate Professor 

Department of Computer Science University of California, Los Angeles

联系方式

yzsun@cs.ucla.edu 

个人简介

Yizhou Sun is an associate professor at department of computer science of UCLA. Prior to that, she was an assistant professor in the College of Computer and Information Science of Northeastern University. She received her Ph.D. in Computer Science from the University of Illinois at Urbana-Champaign in 2012. Her principal research interest is on mining graphs/networks, and more generally in data mining, machine learning, and network science, with a focus on modeling novel problems and proposing scalable algorithms for large-scale, real-world applications. She is a pioneer researcher in mining heterogeneous information network, with a recent focus on deep learning on graphs/networks. Yizhou has over 100 publications in books, journals, and major conferences. Tutorials of her research have been given in many premier conferences. She received 2012 ACM SIGKDD Best Student Paper Award, 2013 ACM SIGKDD Doctoral Dissertation Award, 2013 Yahoo ACE (Academic Career Enhancement) Award, 2015 NSF CAREER Award, 2016 CS@ILLINOIS Distinguished Educator Award, 2018 Amazon Research Award, and 2019 Okawa Foundation Research Grant. 

讲座简介

Graph neural networks (GNNs) have received more and more attention in past several years, due to the wide applications of graphs and networks, and the superiority of their performance compared to traditional heuristics-driven approaches. However, most existing GNNs still focus on node-level applications, such as node classification and link prediction, and many challenging graph tasks are graph-level, such as graph classification and graph similarity search. In this talk, I will introduce our recent progress on graph-level neural operator development. In particular, we will examine two challenging tasks: (1) how can we conduct efficient graph similarity search by turning the NP-Complete GED computation problem into a learning problem? and (2) how can we provide a neural operator that can turn any graph into a low dimensional representation vector, which is learnable, inductive, and unsupervised. In the end, I will briefly introduce our work on graph pre-training, which can learn generic structural features from synthetic graphs and apply to graphs in new domains. 

承办单位

网络与信息系统研究所