用大模型让图神经网络的预测结果变得可懂，尤其适合带文字的图数据。
From Nodes to Narratives: Explaining Graph Neural Networks with LLMs and Graph Context
- 将图神经网络嵌入映射到大模型空间，结合图结构生成自然语言解释。
- 在真实图数据上解释精度高，且解释子图更简洁，人类评估更满意。
- 适合需要理解复杂图模型决策过程的研究者和开发者。
图神经网络（GNN）在结构化数据学习中表现强大，尤其适用于包含文本属性的图（如引文网络、社交平台、知识图谱）。但GNN本身缺乏可解释性，现有方法难以生成精细、可读的解释，尤其当节点属性为丰富自然语言时。本文提出轻量级后处理框架GSPELL，利用大语言模型（LLM）生成忠实且易懂的GNN预测解释。该方法将GNN节点嵌入投影至LLM嵌入空间，构造融合软提示与图结构文本的混合提示，使LLM能推理GNN内部表示并生成自然语言解释及简洁解释子图。在多个真实世界文本属性图数据集上的实验表明，GSPELL在保真度与稀疏性之间取得良好平衡，同时提升人类评估中的洞察力等指标。本工作为基于大模型的图学习可解释性开辟新方向，实现模型内部机制与人类推理的对齐。
原文摘要 · Abstract (English)
Graph Neural Networks (GNNs) have emerged as powerful tools for learning over structured data, including text-attributed graphs (TAGs), which are common in domains such as citation networks, social platforms, and knowledge graphs. GNNs are not inherently interpretable and thus, many explanation methods have been proposed. However, existing explanation methods often struggle to generate interpretable, fine-grained rationales, especially when node attributes include rich natural language. In this work, we introduce GSPELL, a lightweight, post-hoc framework that uses large language models (LLMs) to generate faithful and interpretable explanations for GNN predictions. GSPELL projects GNN node embeddings into the LLM embedding space and constructs hybrid prompts that interleave soft prompts with textual inputs from the graph structure. This enables the LLM to reason about GNN internal representations and to produce natural-language explanations, along with concise explanation subgraphs. Our experiments across real-world TAG datasets demonstrate that GSPELL achieves a favorable trade-off between fidelity and sparsity, while improving human-centric metrics such as insightfulness. GSPELL sets a new direction for LLM-based explainability in graph learning by aligning GNN internals with human reasoning.
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。