Leveraging Large Language Models for Effective Label-free Node Classification in Text-Attributed Graphs

TL;DR

This paper introduces Locle, a cost-effective framework that leverages large language models and graph neural networks for label-free node classification in text-attributed graphs, significantly reducing labeling costs while improving accuracy.

Contribution

Locle is a novel active self-training framework that combines LLMs and GNNs to perform label-free node classification efficiently, addressing noisy labels and query costs.

Findings

Locle outperforms state-of-the-art methods on five benchmark datasets.

Achieves 8.08% accuracy improvement on DBLP with minimal query cost.

Effective in reducing labeling costs to less than one cent.

Abstract

Graph neural networks (GNNs) have become the preferred models for node classification in graph data due to their robust capabilities in integrating graph structures and attributes. However, these models heavily depend on a substantial amount of high-quality labeled data for training, which is often costly to obtain. With the rise of large language models (LLMs), a promising approach is to utilize their exceptional zero-shot capabilities and extensive knowledge for node labeling. Despite encouraging results, this approach either requires numerous queries to LLMs or suffers from reduced performance due to noisy labels generated by LLMs. To address these challenges, we introduce Locle, an active self-training framework that does Label-free node Classification with LLMs cost-Effectively. Locle iteratively identifies small sets of "critical" samples using GNNs and extracts informative pseudo-labels for them with both LLMs and GNNs, serving as additional supervision signals to enhance model training. Specifically, Locle comprises three key components: (i) an effective active node selection strategy for initial annotations; (ii) a careful sample selection scheme to identify "critical" nodes based on label disharmonicity and entropy; and (iii) a label refinement module that combines LLMs and GNNs with a rewired topology. Extensive experiments on five benchmark text-attributed graph datasets demonstrate that Locle significantly outperforms state-of-the-art methods under the same query budget to LLMs in terms of label-free node classification. Notably, on the DBLP dataset with 14.3k nodes, Locle achieves an 8.08% improvement in accuracy over the state-of-the-art at a cost of less than one cent. Our code is available at https://github.com/HKBU-LAGAS/Locle.