GFT: Graph Foundation Model with Transferable Tree Vocabulary

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Zehong, Zhang, Zheyuan, Chawla, Nitesh V, Zhang, Chuxu, Ye, Yanfang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909382652985344
author Wang, Zehong
Zhang, Zheyuan
Chawla, Nitesh V
Zhang, Chuxu
Ye, Yanfang
author_facet Wang, Zehong
Zhang, Zheyuan
Chawla, Nitesh V
Zhang, Chuxu
Ye, Yanfang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_06070
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GFT: Graph Foundation Model with Transferable Tree Vocabulary
Wang, Zehong
Zhang, Zheyuan
Chawla, Nitesh V
Zhang, Chuxu
Ye, Yanfang
Machine Learning
Artificial Intelligence
Social and Information Networks
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.
title GFT: Graph Foundation Model with Transferable Tree Vocabulary
topic Machine Learning
Artificial Intelligence
Social and Information Networks
url https://arxiv.org/abs/2411.06070