OpenGraph: Towards Open Graph Foundation Models

TL;DR

OpenGraph introduces a novel foundation model for graphs that leverages data augmentation with large language models, a unified graph tokenizer, and scalable transformers to enable effective zero-shot learning across diverse and unseen graph data.

Contribution

The paper presents a new graph foundation model, OpenGraph, that improves generalization to unseen graph data through innovative data augmentation, a unified tokenizer, and scalable transformer architecture.

Findings

Achieves state-of-the-art zero-shot performance on various graph tasks.

Effectively generalizes to unseen graph properties and datasets.

Demonstrates robustness across diverse graph domains.

Abstract

Graph learning has become essential in various domains, including recommendation systems and social network analysis. Graph Neural Networks (GNNs) have emerged as promising techniques for encoding structural information and improving performance in tasks like link prediction and node classification. However, a key challenge remains: the difficulty of generalizing to unseen graph data with different properties. In this work, we propose a novel graph foundation model, called OpenGraph, to address this challenge. Our approach tackles several technical obstacles. Firstly, we enhance data augmentation using a large language model (LLM) to overcome data scarcity in real-world scenarios. Secondly, we introduce a unified graph tokenizer that enables the model to generalize effectively to diverse graph data, even when encountering unseen properties during training. Thirdly, our developed scalable graph transformer captures node-wise dependencies within the global topological context. Extensive experiments validate the effectiveness of our framework. By adapting OpenGraph to new graph characteristics and comprehending diverse graphs, our approach achieves remarkable zero-shot graph learning performance across various settings. We release the model implementation at https://github.com/HKUDS/OpenGraph.