Speaker: Zhichun Guo

Date: Feb 2, 11:45am–12:45pm

Abstract: Graph neural networks (GNNs) have been widely used on graph-structured data, but they also face a series of challenges in solving real-world problems, including scarcity of labeled data, scalability issues, and potential bias. In this talk, I will recap my research efforts in tackling these challenges and empowering GNNs on real-world tasks. First, I will start from a specific domain, AI for chemistry, with a focus on addressing the issue of limited labeled datasets commonly encountered in various chemical tasks. Then, I will move to general scenarios and address the inherent issues of GNNs, using scalability as an example. Finally, I will present my future vision and ongoing work aimed at advancing interdisciplinary research and promoting the fairness and robustness of GNNs.

Biographical Sketch: Zhichun Guo is a final-year Ph.D. candidate in the Department of Computer Science and Engineering at the University of Notre Dame. She received her B.S. degree in Computer Science from Fudan University in 2019. At Notre Dame, she has been working with Prof. Nitesh V. Chawla. Her main research interests lie in empowering graph neural networks (GNNs) for real-world tasks, primarily focusing on Chemistry tasks and challenges posed by GNNs. Her work has resulted in 20+ publications in top venues such as ICLR, NeurIPS, ICML, WWW, AAAI, and more. Zhichun’s research achievements have significantly contributed to the AI for Science community and real-world industries. She is the recipient of the 2022 Snap Research Fellowship <https://research.snap.com/fellowships.html> (12 out of the global applicants).

Location and Zoom link: 307 Love, or https://fsu.zoom.us/j/92460894670