提出非线性归因方法，解决传统方法在合作博弈中误判贡献的问题。
Nonlinear Axiomatic Attribution for Cooperative Games
- 基于最小核心思想设计非线性归因框架，保留公平性等核心公理。
- 在包含AUC指标的实验中，新方法显著优于仅放松效率公理的变体。
- 适合需要精准识别关键参与者的研究场景，如模型解释与资源分配。
Shapley值是归因问题中广泛使用的方法，因其唯一满足线性、一致性、平等对待和效率四个公理。然而，其线性特性导致零空间过大，无法区分某些重要扰动，影响对参与者的正向贡献识别。为此，本文探索非线性公理化归因方法的设计。受最小核心这一常见非线性替代方案启发，提出一类保留其余必要公理的非线性归因方法。每种方法均通过最小化问题获得唯一最优贡献向量，以尽可能忠实逼近效用函数。在包含AUC的评估中，实验表明该方法相较于仅放松效率公理的变体更具有效性。代码已开源：https://github.com/watml/nonlinear-axiom。
原文摘要 · Abstract (English)
The Shapley value is a widely used concept in attribution problems, as it uniquely satisfies the axioms of linearity, consistency, equal treatment, and efficiency. Often, the inclusion AUC metric is used to evaluate the quality of player rankings, in order to identify positively participating players. However, it can be established that the Shapley value is not always reliable for this purpose. The core issue lies in its linearity: the Shapley value acts as a linear operator with an excessively large null space, which is likely to contain non-negligible perturbations that remain indistinguishable to the operator. To address this limitation, we explore the design of nonlinear axiomatic attribution methods. Inspired by the least core, which is a popular nonlinear substitute for the Shapley value, we introduce a class of nonlinear attribution methods that retain the remaining necessary axioms. Each method yields a contribution vector that is the unique optimal solution to a minimization problem, which aims to approximate utility functions as faithfully as possible. In terms of the inclusion AUC metric, our experiments demonstrate the potential effectiveness of these methods compared to Shapley value variants that relax only the efficiency axiom. Our code is available at https://github.com/watml/nonlinear-axiom.
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。