用分布外泛化评估图神经网络解释的因果可靠性
Quantifying Explanation Quality in Graph Neural Networks using Out-of-Distribution Generalization
- 基于特征不变性设计解释-泛化评分，衡量解释是否捕捉真实因果因素
- 在11200个模型组合上验证，该评分能有效区分解释的因果有效性
- 适合关注解释可信度与模型可解释性研究的研究者
评估图神经网络（GNN）后验解释的质量仍面临重大挑战。尽管近年来可解释性方法不断涌现，但现有评价指标（如保真度、稀疏性）往往无法判断解释是否识别出真正的潜在因果变量。为此，我们提出解释-泛化评分（EGS），用于量化GNN解释的因果相关性。EGS基于特征不变性原则，认为若解释捕捉到真实的因果驱动因素，则其应能在分布偏移下保持预测稳定。为此，我们构建一个框架：使用解释子图训练GNN，并在分布外（OOD）设置下评估性能（此处OOD泛化作为解释因果有效性的严格代理）。通过涵盖合成数据与真实世界数据的大规模验证（共11,200个模型组合），结果表明EGS为基于解释捕获因果子结构能力提供了一个原理严谨的排序基准，是对传统保真度指标的稳健替代。
原文摘要 · Abstract (English)
Evaluating the quality of post-hoc explanations for Graph Neural Networks (GNNs) remains a significant challenge. While recent years have seen an increasing development of explainability methods, current evaluation metrics (e.g., fidelity, sparsity) often fail to assess whether an explanation identifies the true underlying causal variables. To address this, we propose the Explanation-Generalization Score (EGS), a metric that quantifies the causal relevance of GNN explanations. EGS is founded on the principle of feature invariance and posits that if an explanation captures true causal drivers, it should lead to stable predictions across distribution shifts. To quantify this, we introduce a framework that trains GNNs using explanatory subgraphs and evaluates their performance in Out-of-Distribution (OOD) settings (here, OOD generalization serves as a rigorous proxy for the explanation's causal validity). Through large-scale validation involving 11,200 model combinations across synthetic and real-world datasets, our results demonstrate that EGS provides a principled benchmark for ranking explainers based on their ability to capture causal substructures, offering a robust alternative to traditional fidelity-based metrics.
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。