用代表性节点生成自然语言规则，让GNN全局解释更可信可读。
GnnXemplar: Exemplars to Explanations -- Natural Language Rules for Global GNN Interpretability
- 从嵌入空间选代表节点，通过反向k近邻覆盖最大化来确定
- 在多个基准上比现有方法更准、更快、人类理解度更高
- 适合需要透明决策的工业场景，如金融风控、医疗诊断
图神经网络（GNN）广泛用于节点分类，但其决策过程不透明，限制了信任与应用。尽管局部解释能分析单个预测，但针对整个类别的全局解释仍不成熟。现有全局解释方法依赖小图中的子图模式发现，在真实大图中因子图重复稀少、属性高维、结构-属性交互复杂而失效。我们提出GnnXemplar，受认知科学中范例理论启发，从GNN嵌入空间中识别代表性节点（范例），并基于其邻域生成自然语言规则进行解释。范例选择被建模为反向k近邻上的覆盖最大化问题，采用高效贪心近似求解。为生成可解释规则，使用大语言模型（LLM）的自优化提示策略。在多个基准上的实验表明，GnnXemplar在保真度、可扩展性和人类可读性方面显著优于现有方法，用户研究（60人）验证了其有效性。
原文摘要 · Abstract (English)
Graph Neural Networks (GNNs) are widely used for node classification, yet their opaque decision-making limits trust and adoption. While local explanations offer insights into individual predictions, global explanation methods, those that characterize an entire class, remain underdeveloped. Existing global explainers rely on motif discovery in small graphs, an approach that breaks down in large, real-world settings where subgraph repetition is rare, node attributes are high-dimensional, and predictions arise from complex structure-attribute interactions. We propose GnnXemplar, a novel global explainer inspired from Exemplar Theory from cognitive science. GnnXemplar identifies representative nodes in the GNN embedding space, exemplars, and explains predictions using natural language rules derived from their neighborhoods. Exemplar selection is framed as a coverage maximization problem over reverse k-nearest neighbors, for which we provide an efficient greedy approximation. To derive interpretable rules, we employ a self-refining prompt strategy using large language models (LLMs). Experiments across diverse benchmarks show that GnnXemplar significantly outperforms existing methods in fidelity, scalability, and human interpretability, as validated by a user study with 60 participants.
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。