Trustworthy Computational Science Speaker Series: Jingrui He

Abstract: In transfer learning, the general goal is to leverage the abundant label information from one or more source domains to build a high-performing predictive model in the target domain with limited or no label information. While many research efforts have been focusing on the IID setting where the examples from both the source and target domains are considered to be independent and identically distributed within each domain, recently more research works have been dedicated to the non-IID setting. In particular, many real applications have motivated the study of transferrable graph learning, where the data from both the source and target domains are represented as graphs. In this talk, I will introduce our recent work in this direction using graph neural networks for both regression and classification. For regression, starting from the transferrable Gaussian process for IID data, I will discuss a generic graph-structured Gaussian process framework for adaptively transferring knowledge across graphs with either homophily or heterophily assumptions. For classification, I will present a novel Graph Subtree Discrepancy to measure the graph distribution shift between source and target graphs, which will lead to the generalization error bounds on cross-network transfer learning, including both cross-network node classification and link prediction tasks. Towards the end, I will also discuss the trustworthy aspect of graph transfer learning.

Jingrui He is currently a professor at the School of Information Sciences, University of Illinois at Urbana-Champaign. She also has a courtesy appointment with the Computer Science Department. Dr. He received her Ph.D. from Carnegie Mellon University in 2010. Her research focuses on heterogeneous machine learning, rare category analysis, active learning, and self-supervised learning, with applications in security, social network analysis, healthcare, agriculture, and manufacturing processes. Dr. He is the recipient of the 2016 NSF CAREER Award, the 2020 OAT Award, a three-time recipient of the IBM Faculty Award in 2014, 2015 and 2018, and was selected as IJCAI 2017 Early Career Spotlight. She has more than 160 publications at major conferences (e.g., ICLR, ICML, NeurIPS, IJCAI, AAAI, KDD) and journals (e.g., TKDE, TKDD, DMKD), and is the author of two books. Her papers have received the Distinguished Paper Award at FAccT 2022, as well as Bests of the Conference at ICDM 2016, ICDM 2010, and SDM 2010. Dr. He is a Distinguished Member of ACM, a Senior Member of AAAI, and a Senior Member of IEEE.  

This series, open to the public, is hosted by the Center for Informatics Research in Science and Scholarship (CIRSS). For the Spring 2024 schedule and access to previous talks, visit the Trustworthy Computational Science website. If you are interested in this speaker series, please subscribe to our speaker series calendar: Google Calendar or Outlook Calendar. 

Questions? Contact Janet Eke