Can LLMs Convert Graphs to Text-Attributed Graphs?

TL;DR

This paper introduces TANS, a novel method that uses large language models to convert various types of graphs into text-attributed graphs, enhancing graph learning especially when textual data is scarce.

Contribution

The paper proposes TANS, a new approach leveraging LLMs to generate text-attributed graphs from existing graphs, addressing data scarcity issues in graph neural network applications.

Findings

TANS effectively converts graphs into text-attributed forms across different data types.

It significantly outperforms manual feature design methods on text-free graphs.

The approach demonstrates broad applicability and potential for preprocessing graph data.

Abstract

Graphs are ubiquitous structures found in numerous real-world applications, such as drug discovery, recommender systems, and social network analysis. To model graph-structured data, graph neural networks (GNNs) have become a popular tool. However, existing GNN architectures encounter challenges in cross-graph learning where multiple graphs have different feature spaces. To address this, recent approaches introduce text-attributed graphs (TAGs), where each node is associated with a textual description, which can be projected into a unified feature space using textual encoders. While promising, this method relies heavily on the availability of text-attributed graph data, which is difficult to obtain in practice. To bridge this gap, we propose a novel method named Topology-Aware Node description Synthesis (TANS), leveraging large language models (LLMs) to convert existing graphs into text-attributed graphs. The key idea is to integrate topological information into LLMs to explain how graph topology influences node semantics. We evaluate our TANS on text-rich, text-limited, and text-free graphs, demonstrating its applicability. Notably, on text-free graphs, our method significantly outperforms existing approaches that manually design node features, showcasing the potential of LLMs for preprocessing graph-structured data in the absence of textual information. The code and data are available at https://github.com/Zehong-Wang/TANS.