GraphEdit: Large Language Models for Graph Structure Learning

TL;DR

GraphEdit introduces a novel method using large language models to learn and denoise graph structures, overcoming limitations of traditional GSL methods reliant on explicit structural supervision.

Contribution

This work leverages instruction-tuned LLMs for graph structure learning, enhancing reasoning, denoising noisy connections, and capturing global node dependencies.

Findings

Effective denoising of noisy graph connections

Improved accuracy in node dependency identification

Robust performance across multiple benchmark datasets

Abstract

Graph Structure Learning (GSL) focuses on capturing intrinsic dependencies and interactions among nodes in graph-structured data by generating novel graph structures. Graph Neural Networks (GNNs) have emerged as promising GSL solutions, utilizing recursive message passing to encode node-wise inter-dependencies. However, many existing GSL methods heavily depend on explicit graph structural information as supervision signals, leaving them susceptible to challenges such as data noise and sparsity. In this work, we propose GraphEdit, an approach that leverages large language models (LLMs) to learn complex node relationships in graph-structured data. By enhancing the reasoning capabilities of LLMs through instruction-tuning over graph structures, we aim to overcome the limitations associated with explicit graph structural information and enhance the reliability of graph structure learning. Our approach not only effectively denoises noisy connections but also identifies node-wise dependencies from a global perspective, providing a comprehensive understanding of the graph structure. We conduct extensive experiments on multiple benchmark datasets to demonstrate the effectiveness and robustness of GraphEdit across various settings. We have made our model implementation available at: https://github.com/HKUDS/GraphEdit.