加权Möbius分数：特征归因的统一框架
The Weighted Möbius Score: A Unified Framework for Feature Attribution
AI总结：
本文提出了参数化特征归因框架加权Möbius分数，证明了现有多种特征及交互归因方法为其特例，并利用线性代数工具提供多领域解释，实证验证了其有效性与通用性。
摘要：
特征归因旨在通过识别每个特征对预测的影响来解释黑盒模型预测背后的推理。最近的工作将特征归因扩展到多个特征之间的交互。然而，缺乏统一框架导致方法的激增，这些方法通常无法直接比较。本文引入了一个参数化归因框架——加权Möbius分数——并(i)展示了针对单个特征和特征交互的许多不同归因方法都是其特例，以及(ii)识别了一些新方法。通过研究归因方法的向量空间，我们的框架利用标准线性代数工具，并提供了在各个领域中的解释，包括合作博弈论和因果中介分析。我们通过将这些归因方法应用于情感分析和思维链提示中的特征交互，实证地证明了该框架的通用性和有效性。
英文摘要：
Feature attribution aims to explain the reasoning behind a black-box model's prediction by identifying the impact of each feature on the prediction. Recent work has extended feature attribution to interactions between multiple features. However, the lack of a unified framework has led to a proliferation of methods that are often not directly comparable. This paper introduces a parameterized attribution framework -- the Weighted Möbius Score -- and (i) shows that many different attribution methods for both individual features and feature interactions are special cases and (ii) identifies some new methods. By studying the vector space of attribution methods, our framework utilizes standard linear algebra tools and provides interpretations in various fields, including cooperative game theory and causal mediation analysis. We empirically demonstrate the framework's versatility and effectiveness by applying these attribution methods to feature interactions in sentiment analysis and chain-of-thought prompting.
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。
