Label-free Node Classification on Graphs with Large Language Models (LLMS)¶
Arxiv Link - 2024-02-24 06:44:45
Abstract¶
In recent years, there have been remarkable advancements in node classification achieved by Graph Neural Networks (GNNs). However, they necessitate abundant high-quality labels to ensure promising performance. In contrast, Large Language Models (LLMs) exhibit impressive zero-shot proficiency on text-attributed graphs. Yet, they face challenges in efficiently processing structural data and suffer from high inference costs. In light of these observations, this work introduces a label-free node classification on graphs with LLMs pipeline, LLM-GNN. It amalgamates the strengths of both GNNs and LLMs while mitigating their limitations. Specifically, LLMs are leveraged to annotate a small portion of nodes and then GNNs are trained on LLMs' annotations to make predictions for the remaining large portion of nodes. The implementation of LLM-GNN faces a unique challenge: how can we actively select nodes for LLMs to annotate and consequently enhance the GNN training? How can we leverage LLMs to obtain annotations of high quality, representativeness, and diversity, thereby enhancing GNN performance with less cost? To tackle this challenge, we develop an annotation quality heuristic and leverage the confidence scores derived from LLMs to advanced node selection. Comprehensive experimental results validate the effectiveness of LLM-GNN. In particular, LLM-GNN can achieve an accuracy of 74.9% on a vast-scale dataset \products with a cost less than 1 dollar.
Socials¶
| X | |
|---|---|
| 🚀 Exciting advancements in AI research! A new approach, LLM-GNN, combines Large Language Models and Graph Neural Networks for label-free node classification on graphs. By leveraging LLMs to annotate a small portion of nodes and training GNNs on this data, LLM-GNN achieves impressive accuracy of 74.9% on a large dataset while keeping costs under $1. Learn more about this innovative pipeline here: http://arxiv.org/abs/2310.04668v3 #AI #LLM #GNN #NodeClassification #TechInnovation 🌟 | 🚀 Exciting developments in AI research! Introducing LLM-GNN, a novel pipeline for label-free node classification on graphs. By combining Large Language Models and Graph Neural Networks, LLM-GNN achieves 74.9% accuracy on a large dataset with minimal cost. Learn more at: http://arxiv.org/abs/2310.04668v3 #AI #LLM #GNN #NodeClassification |