让图神经网络用人类可读文本表达隐藏状态，提升可解释性。
'Hello, World!': Making GNNs Talk with LLMs
- 将GNN的隐状态转化为自然语言，通过提示工程融合图注意力与残差连接
- 在节点分类和链接预测任务上实现强零样本性能，超越现有LLM基线方法
- 适合关注模型可解释性与图学习机制分析的研究者
尽管图神经网络（GNN）在各类图相关任务中表现出色，但其高维隐藏表示使其成为黑箱。本文提出图语言网络（GLN），一种基于大语言模型（LLM）构建的GNN，其隐藏表示以人类可读的文本形式存在。通过精心设计的提示，GLN不仅包含GNN的消息传递模块，还融合了图注意力和初始残差连接等先进技术。GLN的可理解隐藏表示使我们能够直观分析节点表示在（1）不同层间的变化，以及（2）在先进GNN技术下的演化，揭示了GNN内部工作机制。此外，我们证明了GLN在节点分类和链接预测任务上实现了优异的零样本性能，优于现有的基于LLM的基线方法。
原文摘要 · Abstract (English)
While graph neural networks (GNNs) have shown remarkable performance across diverse graph-related tasks, their high-dimensional hidden representations render them black boxes. In this work, we propose Graph Lingual Network (GLN), a GNN built on large language models (LLMs), with hidden representations in the form of human-readable text. Through careful prompt design, GLN incorporates not only the message passing module of GNNs but also advanced GNN techniques, including graph attention and initial residual connection. The comprehensibility of GLN's hidden representations enables an intuitive analysis of how node representations change (1) across layers and (2) under advanced GNN techniques, shedding light on the inner workings of GNNs. Furthermore, we demonstrate that GLN achieves strong zero-shot performance on node classification and link prediction, outperforming existing LLM-based baseline methods.
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。