将图结构转为文本或标记，用大模型理解图数据
Graph2text or Graph2token: A Perspective of Large Language Models for Graph Learning
- 提出Graph2text和Graph2token两种图转文本的思路
- 系统梳理方法并指出四大转换挑战
- 适合想用大模型处理图数据的研究者参考
图是表示不规则网络的数据结构，在众多现实应用中广泛存在。以往方法直接建模图结构并取得显著成效，但受限于图的内在不规则性。一种创新方案是将图转化为文本表示，从而利用大语言模型（LLM）的强大能力来处理和理解图。本文全面综述了将LLM应用于图学习的方法，称为LLM4graph。其核心在于将图转换为文本，使LLM能够理解和分析。为此，我们从转换视角提出新的分类体系，现有方法可分为两大范式：Graph2text（将图转为文本）和Graph2token（将图转为标记）。我们指出了转换过程中的四大挑战，以问题导向系统呈现现有方法。针对实际需求，提供在不同图类型和硬件限制下选择合适模型与LLM的指南，并识别出五个未来研究方向。
原文摘要 · Abstract (English)
Graphs are data structures used to represent irregular networks and are prevalent in numerous real-world applications. Previous methods directly model graph structures and achieve significant success. However, these methods encounter bottlenecks due to the inherent irregularity of graphs. An innovative solution is converting graphs into textual representations, thereby harnessing the powerful capabilities of Large Language Models (LLMs) to process and comprehend graphs. In this paper, we present a comprehensive review of methodologies for applying LLMs to graphs, termed LLM4graph. The core of LLM4graph lies in transforming graphs into texts for LLMs to understand and analyze. Thus, we propose a novel taxonomy of LLM4graph methods in the view of the transformation. Specifically, existing methods can be divided into two paradigms: Graph2text and Graph2token, which transform graphs into texts or tokens as the input of LLMs, respectively. We point out four challenges during the transformation to systematically present existing methods in a problem-oriented perspective. For practical concerns, we provide a guideline for researchers on selecting appropriate models and LLMs for different graphs and hardware constraints. We also identify five future research directions for LLM4graph.
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。