通过证据权重评估特征重要性解释的对齐性与稳定性
Assessing Alignment and Stability of Feature Importance Explanations via Weight of Evidence
浏览论文内容
中文总结 AI 辅助
本研究将特征重要性方法（FIMs）嵌入证据权重（WoE）的假设检验框架，提出可评估FIMs对齐性与稳定性的新方法，并通过LIME、SHAP的实证分析验证了策略的适用性。
中文摘要 AI 辅助
特征重要性方法（Feature Importance Methods, FIMs）广泛应用于可解释人工智能中以解释模型预测结果，但仅归因分数往往无法为底层推理过程提供充足洞见。本研究提出一种新视角，将FIMs嵌入基于证据权重（Weight of Evidence, WoE）的假设检验框架中，量化观测证据对任意给定特征重要性假设的支持强度。参考假设可源自领域知识、真实值或由FIM自身推导得出，该公式化方法可实现对FIMs的原则性评估，同时捕捉其与先验知识的对齐性及变异性。我们进一步提供将WoE与归因方差关联的理论结果，实证结果显示该策略在分析不同参考假设场景下的LIME与SHAP解释时具有适用性与灵活性。总体而言，本框架为通过对比式、基于证据的视角评估FIMs提供了一种互补工具。
英文摘要
Feature importance Methods (FIMs) are widely used in Explainable AI to interpret model predictions, yet attribution scores alone often provide limited insight into the underlying reasoning process. In this work, we introduce a novel perspective by embedding FIMs within a hypothesis-testing framework based on Weight of Evidence (WoE). We quantify how strongly the observed evidence supports any given hypothesis on feature importance. The reference hypothesis can stem from domain knowledge, ground truth, or be derived from the FIM itself. This formulation enables a principled evaluation of FIMs, capturing both their alignment with prior knowledge and their variability. We further provide theoretical results linking WoE to attribution variance. Empirical results shows the applicability and flexibility of our strategy analyzing LIME and SHAP explanations in settings with different reference hypotheses. Overall, our framework offers a complementary tool for assessing FIMs through a contrastive, evidence-based lens.
发表机构
- SMARTEST Research Center（SMARTEST研究中心）
- eCampus University（eCampus大学）
- Barcelona Supercomputing Center（巴塞罗那超级计算中心）
- University of Florence（佛罗伦萨大学）
- University of Pisa（比萨大学）
机构由 AI 辅助整理，请以论文原文为准。
