性别与公平的机器学习有什么关系？
What's Sex Got To Do With Fair Machine Learning?
摘要：
关于机器学习公平性的争论主要集中在对群体之间公平或非歧视要求的竞争定义上。然而，很少有人注意到一个群体到底是什么。许多最近的方法“公平”需要一个指定的因果模型的数据生成过程。这些练习做了一个隐含的本体论假设，即种族或性别群体只是共享给定特征的个体的集合。我们通过探索因果模型中的模块化的正式假设来证明这一点，该假设认为，一个因果路径捕获的依赖关系对于任何其他路径的干预都是不变的。性的因果模型提出了两个实质性的主张：1）存在一个特征，性本身，这是一个个体的内在特质，它因果地在世界上带来了外部的社会现象; 2）性及其影响之间的关系可以以任何方式修改，前一个特征仍然保留了性在我们世界中的意义。我们认为，这种本体论的图片是错误的。许多所谓性“造成”的“影响”，实际上是性作为一种社会地位的构成特征。它们赋予了性别特征的社会意义，正是这些意义使性别歧视成为一种明显的道德问题行为。纠正这一概念上的错误对如何使用模型来发现歧视有许多影响。构成关系的形式图为歧视的推理提供了一条完全不同的道路。因果图指导复杂的模块化反事实的构建，而构成图确定了一种不同类型的反事实作为歧视调查的核心：一个群体的社会意义将如何改变，如果它的非模块化特征被改变。
英文摘要：
Debate about fairness in machine learning has largely centered around competing definitions of what fairness or nondiscrimination between groups requires. However, little attention has been paid to what precisely a group is. Many recent approaches to "fairness" require one to specify a causal model of the data generating process. These exercises make an implicit ontological assumption that a racial or sex group is simply a collection of individuals who share a given trait. We show this by exploring the formal assumption of modularity in causal models, which holds that the dependencies captured by one causal pathway are invariant to interventions on any other pathways. Causal models of sex propose two substantive claims: 1) There exists a feature, sex-on-its-own, that is an inherent trait of an individual that causally brings about social phenomena external to it in the world; and 2) the relations between sex and its effects can be modified in whichever ways and the former feature would still retain the meaning that sex has in our world. We argue that this ontological picture is false. Many of the "effects" that sex purportedly "causes" are in fact constitutive features of sex as a social status. They give the social meaning of sex features, meanings that are precisely what make sex discrimination a distinctively morally problematic type of action. Correcting this conceptual error has a number of implications for how models can be used to detect discrimination. Formal diagrams of constitutive relations present an entirely different path toward reasoning about discrimination. Whereas causal diagrams guide the construction of sophisticated modular counterfactuals, constitutive diagrams identify a different kind of counterfactual as central to an inquiry on discrimination: one that asks how the social meaning of a group would be changed if its non-modular features were altered.
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。
