论博弈论特征归因与反事实解释之间的联系
On the Connection between Game-Theoretic Feature Attributions and Counterfactual Explanations
AI总结：
本文建立博弈论特征归因（以 SHAP 为代表）与反事实解释的理论等价关系，扩展至更多博弈论解概念，并通过三数据集实验验证相关条件与局限。
摘要：
近年来，可解释人工智能（XAI）受到了广泛关注，其中最受欢迎的两类解释是特征归因和反事实解释。这两类方法在很大程度上是被独立研究的，而少数试图调和它们的尝试主要是经验性的。本工作在博弈论特征归因（重点关注但不限于 SHAP）与反事实解释之间建立了清晰的理论联系。在推动对基于 Shapley 值的特征归因和反事实解释进行操作性修改之后，我们证明了在一定条件下它们实际上是等价的。随后，我们将这一等价性结果扩展到 Shapley 值之外的博弈论解概念。此外，通过分析这种等价性的条件，我们揭示了朴素地使用反事实解释来提供特征重要性的局限性。在三个数据集上的实验定量展示了两种方法之间联系的每个阶段中解释的差异，并证实了理论发现。
英文摘要：
Explainable Artificial Intelligence (XAI) has received widespread interest in recent years, and two of the most popular types of explanations are feature attributions, and counterfactual explanations. These classes of approaches have been largely studied independently and the few attempts at reconciling them have been primarily empirical. This work establishes a clear theoretical connection between game-theoretic feature attributions, focusing on but not limited to SHAP, and counterfactuals explanations. After motivating operative changes to Shapley values based feature attributions and counterfactual explanations, we prove that, under conditions, they are in fact equivalent. We then extend the equivalency result to game-theoretic solution concepts beyond Shapley values. Moreover, through the analysis of the conditions of such equivalence, we shed light on the limitations of naively using counterfactual explanations to provide feature importances. Experiments on three datasets quantitatively show the difference in explanations at every stage of the connection between the two approaches and corroborate the theoretical findings.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
