Disentangled Representation Learning with Large Language Models for Text-Attributed Graphs

TL;DR

This paper introduces DGTL, a model that enhances large language models' understanding of text-attributed graphs by integrating disentangled graph neural networks, improving reasoning, prediction, and interpretability.

Contribution

The paper proposes DGTL, a novel approach combining GNN layers with frozen LLMs to better capture complex structural relationships in TAGs, with improved efficiency and interpretability.

Findings

DGTL outperforms state-of-the-art baselines in TAG tasks.

DGTL provides natural language explanations for its predictions.

The model operates efficiently with frozen pre-trained LLMs.

Abstract

Text-attributed graphs (TAGs) are prevalent on the web and research over TAGs such as citation networks, e-commerce networks and social networks has attracted considerable attention in the web community. Recently, large language models (LLMs) have demonstrated exceptional capabilities across a wide range of tasks. However, the existing works focus on harnessing the potential of LLMs solely relying on prompts to convey graph structure information to LLMs, thus suffering from insufficient understanding of the complex structural relationships within TAGs. To address this problem, in this paper we present the Disentangled Graph-Text Learner (DGTL) model, which is able to enhance the reasoning and predicting capabilities of LLMs for TAGs. Our proposed DGTL model incorporates graph structure information through tailored disentangled graph neural network (GNN) layers, enabling LLMs to capture the intricate relationships hidden in text-attributed graphs from multiple structural factors. Furthermore, DGTL operates with frozen pre-trained LLMs, reducing computational costs and allowing much more flexibility in combining with different LLM models. Experimental evaluations demonstrate the effectiveness of the proposed DGTL model on achieving superior or comparable performance over state-of-the-art baselines. Additionally, we also demonstrate that our DGTL model can offer natural language explanations for predictions, thereby significantly enhancing model interpretability.