TAMIDS Tutorial Series: Shuiwang Ji: Frontiers of Graph Neural Networks with the Dive-Into-Graphics (DIG) Library

Speaker: Shuiwang Ji, Ph.D. Professor, Computer Science & Engineering, Texas A&M University

Faculty Host: Yu Ding, TAMIDS

Abstract: Graph deep learning has been drawing increasing attention due to its effectiveness in learning from rich graph data. It has achieved remarkable successes in many domains such as social networks, drug discovery, and physical simulations. Recently, several frontier research topics of graph neural networks (GNNs) enable more effective and trustworthy models for graph deep learning. Specifically, self-supervised learning is emerging as a promising paradigm to make use of large amounts of unlabeled graph data to boost the GNN performance under limited label availability. In addition, the study of explainability enables human-intelligible explanations for the black-box GNN models to build trustworthy AI by identifying important graph substructures that contribute to model decisions. In the tutorial, the speakers will cover fundamentals of GNNs, challenges, and up-to-date approaches of the two frontier topics. The speakers will also introduce the DIG library for graph deep learning research with hands-on demonstrations.

Biography: Dr. Shuiwang Ji is currently a Professor and Presidential Impact Fellow in the Department of Computer Science and Engineering, Texas A&M University. His research interests include artificial intelligence, machine learning, and graph analysis. This tutorial is to be assisted by his Ph.D. students, Yaochen Xie, Zhao Xu, and Haiyang Yu.

Link to PDF version

You can also click this link to join the seminar

For more information about TAMIDS seminar series, please contact Ms. Jennifer South at jsouth@tamu.edu