提出因果可解释性方法，分析收入不平等的根源
Counterfactual explainability and analysis of variance
- 基于因果图构建依赖变量的反事实解释框架
- 在真实数据中验证性别、种族、教育对收入差异的影响
- 适合研究社会公平与政策评估的学者使用
现有模型解释工具多为相关性分析，缺乏因果机制理解。本文提出一种新的反事实可解释性概念，受双胞胎研究中遗传力启发，将全局敏感性分析（如方差分解和Sobol指数）从独立变量扩展至有因果关系的依赖变量，通过有向无环图描述变量间因果结构。该度量方法天然包含因果机制。在同调性假设下，提出估计方法，并应用于真实数据，解释性别、种族与教育程度对收入不平等的影响。
原文摘要 · Abstract (English)
Existing tools for explaining complex models and systems are associational rather than causal and do not provide mechanistic understanding. We propose a new notion called counterfactual explainability for causal attribution that is motivated by the concept of genetic heritability in twin studies. Counterfactual explainability extends methods for global sensitivity analysis (including the functional analysis of variance and Sobol's indices), which assumes independent explanatory variables, to dependent explanations by using a directed acyclic graphs to describe their causal relationship. Therefore, this explanability measure directly incorporates causal mechanisms by construction. Under a comonotonicity assumption, we discuss methods for estimating counterfactual explainability and apply them to a real dataset dataset to explain income inequality by gender, race, and educational attainment.
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。