Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

4-2025

Abstract

Graphs are able to model interconnected entities in many online services, supporting a wide range of applications on the Web. This raises an important question: How can we train a graph foundational model on multiple source domains and adapt to an unseen target domain? A major obstacle is that graphs from different domains often exhibit divergent characteristics. Some studies leverage large language models to align multiple domains based on textual descriptions associated with the graphs, limiting their applicability to text-attributed graphs. For text-free graphs, a few recent works attempt to align different feature distributions across domains, while generally neglecting structural differences. In this work, we propose a novel Structure Alignment framework for text-free Multi-domain Graph Pre-Training and cross-domain adaptation (SAMGPT). It is designed to learn multi-domain knowledge from graphs originating in multiple source domains, which can then be adapted to address applications in an unseen target domain. Specifically, we introduce a set of structure tokens to harmonize structure-based aggregation across source domains during the pre-training phase. Next, for cross-domain adaptation, we design dual prompts, namely, holistic prompts and specific prompts, which adapt unified multi-domain structural knowledge and fine-grained, domain-specific information, respectively, to a target domain. Finally, we conduct comprehensive experiments on seven public datasets to evaluate and analyze the effectiveness of SAMGPT.

Keywords

Graph learning, foundation models, multi-domain pre-training, prompt learning, few-shot learning

Discipline

Artificial Intelligence and Robotics | Graphics and Human Computer Interfaces

Areas of Excellence

Digital transformation

Publication

WWW '25: The ACM Web Conference 2025, Sydney, Australia, April 28 - May 2

First Page

1142

Last Page

1153

Identifier

10.1145/3696410.3714828

Publisher

ACM

City or Country

New York

Additional URL

https://doi.org/10.1145/3696410.3714828

Download

Share

COinS