Boosting Graph Foundation Model from Structural Perspective

TL;DR

This paper introduces BooG, a novel graph foundation model that leverages virtual super nodes and contrastive pre-training to unify structural features across domains, enhancing generalizability and performance.

Contribution

The paper proposes a new structural perspective for graph foundation models using virtual super nodes and contrastive learning, addressing domain-specific structural differences.

Findings

BooG outperforms existing models on various datasets and tasks.

The use of virtual super nodes improves cross-domain structural unification.

Contrastive pre-training enhances the expressiveness and generalization of graph representations.

Abstract

Graph foundation models have recently attracted significant attention due to its strong generalizability. Although existing methods resort to language models to learn unified semantic representations across domains, they disregard the unique structural characteristics of graphs from different domains. To address the problem, in this paper, we boost graph foundation model from structural perspective and propose BooG. The model constructs virtual super nodes to unify structural characteristics of graph data from different domains. Specifically, the super nodes fuse the information of anchor nodes and class labels, where each anchor node captures the information of a node or a graph instance to be classified. Instead of using the raw graph structure, we connect super nodes to all nodes within their neighborhood by virtual edges. This new structure allows for effective information aggregation while unifying cross-domain structural characteristics. Additionally, we propose a novel pre-training objective based on contrastive learning, which learns more expressive representations for graph data and generalizes effectively to different domains and downstream tasks. Experimental results on various datasets and tasks demonstrate the superior performance of BooG. We provide our code and data here: https://anonymous.4open.science/r/BooG-EE42/.