Can LLMs Convert Graphs to Text-Attributed Graphs?

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Zehong, Liu, Sidney, Zhang, Zheyuan, Ma, Tianyi, Zhang, Chuxu, Ye, Yanfang
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912223031459840
author Wang, Zehong
Liu, Sidney
Zhang, Zheyuan
Ma, Tianyi
Zhang, Chuxu
Ye, Yanfang
author_facet Wang, Zehong
Liu, Sidney
Zhang, Zheyuan
Ma, Tianyi
Zhang, Chuxu
Ye, Yanfang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_10136
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Can LLMs Convert Graphs to Text-Attributed Graphs?
Wang, Zehong
Liu, Sidney
Zhang, Zheyuan
Ma, Tianyi
Zhang, Chuxu
Ye, Yanfang
Computation and Language
Artificial Intelligence
Machine Learning
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.
title Can LLMs Convert Graphs to Text-Attributed Graphs?
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2412.10136