Integrating Relational Learning in Foundation Models 

Date: 4 July 2025 (Fri.)

Time: 10:30 - 11:30 am HKT

Language: English

Venue

W1-102, HKUST GZ Campus

Online Tencent Meeting

911-137-301

https://meeting.tencent.com/dm/IvkWsb5t0TjH

（阅读原文进行跳转）

Despite many generations of algorithms and deep learning models for relational data, existing state-of-the-art methods, even including foundation models, have not converged to a satisfactory solution towards universal, general and practical graph intelligence. As one of the most general yet underexplored modalities, problems in the form of graphs, relational data and geometry pose some of the ultimate challenges in deep learning. This talk explores reasons why such machine learning problems are so challenging, and potential directions where foundation models can interact with graph data towards this goal. We proposed models that integrates graphs with foundation models to synergistically solve problems that require reasoning in multiple modalities, demonstrating examples where foundation model approaches improves graph learning; and where graph structure enhances LLM reliability. Finally, these new challenging tasks help redefine the problem settings and use cases towards more realistic and meaningful applications of graph and geometry, therefore necessitate new benchmarks and evaluation for future research. We demonstrate this via downstream large-scale applications of literature foundation models and domain-specific AI agents.