Graph Foundation Models (GFMs) is a single (neural) model that learns transferable graph representations that can generalize to any new, previously unseen graph. In this talk, we will introduce: (1) The long-term technical goal will the GFMs serve (2) The knowledge gap in the graph domain the GFMs can fill (3) The critical problem GFMs can solve.
Speaker Bio
Haitao Mao is the final year PhD student in Michigan State University. His research interests lies in developing Graph Foundation Model grounded in network science and LLMs for pragmatics. He is the organizer of LOG conferenece 2023. He won the CIKM 2021 best short award and WSDM 2024 best paper honor mention award as the first author. https://haitaomao.github.io/me/
More Details
- When: Wed 11 Sept 2024, at 1:00 - 2:00 pm (GMT+10)
- Speaker: Haitao Mao (Michigan State University)
- Host: Ruihong Qiu
- Venue: Online
- Zoom: https://uqz.zoom.us/j/84584183045 [Recording]
No.24-07 Embracing Changes in Deep Learning: Continual Learning with Augmented and Modularized Memory