大模型与图神经网络融合，提升图数据挖掘能力
Large Language Models Meet Graph Neural Networks: A Perspective of Graph Mining
- 提出三类融合模式：图驱动大模型、大模型驱动图、协同驱动
- 大模型增强图特征提取，提升节点分类等任务效果
- 适合对图学习和大模型交叉应用感兴趣的 researchers
图挖掘是数据挖掘与机器学习中的重要领域，旨在从图结构数据中提取有价值信息。近年来，图神经网络（GNNs）在此领域取得显著进展，但仍面临在多样化图数据上泛化能力不足的问题。为解决此问题，大型语言模型（LLMs）凭借其卓越的语义理解能力，为图挖掘任务提供了新思路。本文系统综述了LLMs与GNNs的结合与应用技术，提出了一个全新的研究分类体系，涵盖三大类别：GNN-driving-LLM、LLM-driving-GNN、GNN-LLM-co-driving。在此框架下，揭示了LLMs在提升图特征提取能力及增强下游任务（如节点分类、链接预测、社区检测）有效性方面的潜力。尽管LLMs在处理图结构数据方面展现出巨大前景，其高计算开销与复杂性仍是挑战。未来研究需持续探索如何高效融合二者，以实现更强大的图学习与推理能力，推动图挖掘技术发展。
原文摘要 · Abstract (English)
Graph mining is an important area in data mining and machine learning that involves extracting valuable information from graph-structured data. In recent years, significant progress has been made in this field through the development of graph neural networks (GNNs). However, GNNs are still deficient in generalizing to diverse graph data. Aiming to this issue, Large Language Models (LLMs) could provide new solutions for graph mining tasks with their superior semantic understanding. In this review, we systematically review the combination and application techniques of LLMs and GNNs and present a novel taxonomy for research in this interdisciplinary field, which involves three main categories: GNN-driving-LLM, LLM-driving-GNN, and GNN-LLM-co-driving. Within this framework, we reveal the capabilities of LLMs in enhancing graph feature extraction as well as improving the effectiveness of downstream tasks such as node classification, link prediction, and community detection. Although LLMs have demonstrated their great potential in handling graph-structured data, their high computational requirements and complexity remain challenges. Future research needs to continue to explore how to efficiently fuse LLMs and GNNs to achieve more powerful graph learning and reasoning capabilities and provide new impetus for the development of graph mining techniques.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。