提出新方法超越经典分值，让模型解释更灵活可靠。
Beyond Shapley Values: Cooperative Games for the Interpretation of Machine Learning Models
- 用韦伯集和哈桑尼集替代固定公理，扩展解释工具
- 区分价值函数与聚合规则，提升解释一致性
- 提供三步框架，适合追求理论严谨的解释研究者
合作博弈论已成为机器学习后验可解释性的核心，主要依赖于谢帕利值。然而，尽管应用广泛，基于谢帕利值的方法常建立在与其特征归因相关性存疑的公理基础上。本文从可解释性视角重新审视合作博弈论，主张更广泛且更具原则性的工具使用。我们指出两类高效分配方案——韦伯集和哈桑尼集——可超越谢帕利值，提供更丰富的解释灵活性。本文系统梳理了这些分配机制，厘清价值函数与聚合规则的区别，并提出一个三步构建流程，用于设计可靠且理论基础牢固的特征归因方法。目标是摆脱固定公理束缚，为XAI领域提供一套连贯框架，支持设计既有意义又适应方法演进的归因方法。
原文摘要 · Abstract (English)
Cooperative game theory has become a cornerstone of post-hoc interpretability in machine learning, largely through the use of Shapley values. Yet, despite their widespread adoption, Shapley-based methods often rest on axiomatic justifications whose relevance to feature attribution remains debatable. In this paper, we revisit cooperative game theory from an interpretability perspective and argue for a broader and more principled use of its tools. We highlight two general families of efficient allocations, the Weber and Harsanyi sets, that extend beyond Shapley values and offer richer interpretative flexibility. We present an accessible overview of these allocation schemes, clarify the distinction between value functions and aggregation rules, and introduce a three-step blueprint for constructing reliable and theoretically-grounded feature attributions. Our goal is to move beyond fixed axioms and provide the XAI community with a coherent framework to design attribution methods that are both meaningful and robust to shifting methodological trends.
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。