用因果推理生成可解释的图神经网络决策依据
CIExplainer++: Generating Causal and Interpretable Explanations for Graph Neural Networks
- 基于因果推断的扰动方法，识别影响预测的关键子图
- 在多种GNN模型和数据集上验证，显著提升解释可信度
- 将子图转化为自然语言，兼顾特征与关系信息
可解释人工智能旨在通过以人类可理解的方式呈现模型输出的关键要素，增强黑箱模型的可信度。这需要同时满足两个条件：(i) 识别对输出具有真实因果影响的组件及关联；(ii) 将这些结构转化为可解释的表达形式。为此，本文提出CIExplainer，一种基于因果推断的新型扰动方法，用于解释图神经网络（GNNs）。CIExplainer利用潜在结果框架，识别对GNN预测具有最大因果效应的子图。我们在多种GNN架构（GCN、GraphSAGE、GAT、GIN）和数据集上评估并比较了CIExplainer的表现。为进一步实现子图解释与人类可读性之间的衔接，我们提出G2TeXplainer，该方法将因果子图转换为包含特征级与关系级信息的自然语言解释。
原文摘要 · Abstract (English)
Explainable Artificial Intelligence aims to make black-box models more trustworthy by presenting, in a human-understandable manner, the elements that lead to the model's output. This involves both (i) identifying components and connections with genuine causal influence on outputs and (ii) translating such structures into an interpretable representation. For the former, we introduce CIExplainer, a novel perturbation-based method grounded in causal inference for explaining Graph Neural Networks (GNNs). CIExplainer identifies the subgraph with the highest causal effects on GNN predictions using the Potential Outcome Framework. We evaluate and compare CIExplainer on various GNN architectures (GCN, GraphSAGE, GAT, GIN) and datasets. To bridge subgraph explanations with human interpretability, we further propose G2TeXplainer, a method that transforms causal subgraphs into natural language explanations that capture both feature-level and relational information.
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。