GFT: Graph Foundation Model with Transferable Tree Vocabulary

TL;DR

This paper introduces GFT, a graph foundation model that uses transferable computation trees as a vocabulary to improve generalization across various graph tasks and domains.

Contribution

We propose a novel GFT model that encodes transferable computation trees as tokens, enabling cross-task and cross-domain transferability in graph learning.

Findings

GFT demonstrates improved generalization across multiple graph tasks.

Transferable computation trees are effective as a shared vocabulary.

Theoretical analysis confirms the transferability of computation trees.

Abstract

Inspired by the success of foundation models in applications such as ChatGPT, as graph data has been ubiquitous, one can envision the far-reaching impacts that can be brought by Graph Foundation Models (GFMs) with broader applications in the areas such as scientific research, social network analysis, drug discovery, and e-commerce. Despite the significant progress of pre-trained graph neural networks, there haven't been GFMs that can achieve desired performance on various graph-learning-related tasks. Building GFMs may rely on a vocabulary that encodes transferable patterns shared among different tasks and domains. Unlike image and text, defining such transferable patterns for graphs remains an open question. In this paper, we aim to bridge this gap by rethinking the transferable patterns on graphs as computation trees -- i.e., tree structures derived from the message-passing process. Based on this insight, we propose a cross-task, cross-domain graph foundation model named GFT, short for Graph Foundation model with transferable Tree vocabulary. By treating computation trees as tokens within the transferable vocabulary, GFT improves model generalization and reduces the risk of negative transfer. The theoretical analyses and extensive experimental studies have demonstrated the transferability of computation trees and shown the effectiveness of GFT across diverse tasks and domains in graph learning. The open source code and data are available at https://github.com/Zehong-Wang/GFT.