Toward General and Robust LLM-enhanced Text-attributed Graph Learning

ACL ARR 2025 May Submission231 Authors

Abstract: Recent advancements in Large Language Models (LLMs) and the proliferation of Text-Attributed Graphs (TAGs) across various domains have positioned LLM-enhanced TAG learning as a critical research area. However, the field faces significant challenges: (1) the absence of a unified framework to systematize the diverse optimization perspectives, and (2) the lack of a robust method capable of handling real-world TAGs, which often suffer from texts and edge sparsity, leading to suboptimal performance.To address these challenges, we propose UltraTAG, a unified pipeline for LLM-enhanced TAG learning. UltraTAG provides a unified comprehensive and domain-adaptive framework in the field. Building on this framework, we propose UltraTAG-S, a robust instantiation of UltraTAG designed to tackle the inherent sparsity issues in real-world TAGs with the technology of LLM-based text propagation, text augmentation, and edge reconfiguration strategies. Our extensive experiments demonstrate that UltraTAG-S significantly outperforms existing baselines, achieving improvements of 2.12\% and 17.47\% in ideal and sparse settings, respectively. Moreover, as the data sparsity ratio increases, the performance improvement of UltraTAG-S also rises.

Paper Type: Long

Research Area: Machine Learning for NLP

Research Area Keywords: graph-based methods, data augmentation

Languages Studied: English

Keywords: Graph Neural Networks, Large Language Models, Sparsity, Text-Attributed Graph

Submission Number: 231