修复了SHAP值在可解释AI中的误导性问题，提出更可靠的解释方法。
The Explanation Game -- Rekindled (Extended Version)
- 提出新型SHAP值定义，解决现有方法的根本缺陷。
- 实验证明旧版SHAP值可能误导决策者，新方法显著改善可靠性。
- 提供高效估算方案，适合需要可信解释的工业级应用。
近期研究揭示了当前可解释AI中使用Shapley值（即SHAP分数）存在的关键缺陷，这些缺陷可能导致向人类决策者提供的解释具有误导性。尽管这些负面结果看似表明应放弃使用Shapley值，本文却持相反观点。具体而言，本文提出了一个克服现有缺陷的新版SHAP分数定义，并给出了该新分数的高效估算方法。初步实验结果验证了本文主张，进一步凸显了现有SHAP分数的不足。
原文摘要 · Abstract (English)
Recent work demonstrated the existence of critical flaws in the current use of Shapley values in explainable AI (XAI), i.e. the so-called SHAP scores. These flaws are significant in that the scores provided to a human decision-maker can be misleading. Although these negative results might appear to indicate that Shapley values ought not be used in XAI, this paper argues otherwise. Concretely, this paper proposes a novel definition of SHAP scores that overcomes existing flaws. Furthermore, the paper outlines a practically efficient solution for the rigorous estimation of the novel SHAP scores. Preliminary experimental results confirm our claims, and further underscore the flaws of the current SHAP scores.
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。