No.24-09 Graph Foundation Model in the Era of LLMs

Graph data structures play a crucial role in real life, effectively illustrating the complex relationships and structural dependencies between entities. In recent years, the generalization capabilities of graph models have garnered significant attention. We can’t help but wonder about the possibilities that could emerge if we fully leveraged large models to address these challenges. This is the central focus of our research: developing large language models and foundational models specifically tailored for graph data. Our strategy involves designing LLMs that can effectively encode and reason about graph structures, capturing the intricate relationships among entities. By applying the principles of language models to the domain of graph data, we aim to deepen our understanding of graph structures, ultimately achieving more powerful and scalable graph analysis to tackle real-world challenges in learning data relationships.

Speaker Bio

Chao Huang is an Assistant Professor and PhD supervisor in the Department of Computer Science and the Institute of Data Science at the University of Hong Kong. His research interests encompass large language models (LLMs), graph learning, recommender systems, and spatiotemporal data mining. His research papers in these areas have garnered widespread recognition, being regarded as some of the most influential and highly cited works at conferences such as KDD 2024, WSDM 2024, WWW 2024/2023, SIGIR 2024/2023/2022, and KDD 2019. Additionally, his research has received nominations for Best Paper Awards at conferences including WWW 2023, WSDM 2022, and WWW 2019. His academic contributions have earned him the title of “Rising Star” at the WAIC World Artificial Intelligence Conference (WAIC), as well as the “2024 Frontier Science Award in Theoretical Computer Science and Information Science.” https://sites.google.com/view/chaoh

More Details

• When: Wed 16 Oct 2024, at 1:00 - 2:00 pm (GMT+10)
• Speaker: Prof Chao Huang (University of Hong Kong)
• Host: Dr Ruihong Qiu
• Venue: Online
• Zoom: https://uqz.zoom.us/j/88003098168