A decision can be defined as fair if equal individuals are treated equally and unequals unequally. Adopting this definition, the task of designing machine learning (ML) models that mitigate unfairness in automated decision-making systems must include causal thinking when introducing protected attributes: Following a recent proposal, we define individuals as being normatively equal if they are equal in a fictitious, normatively desired (FiND) world, where the protected attributes have no (direct or indirect) causal effect on the target. We propose rank-preserving interventional distributions to define a specific FiND world in which this holds and a warping method for estimation. Evaluation criteria for both the method and the resulting ML model are presented and validated through simulations. Experiments on empirical data showcase the practical application of our method and compare results with "fairadapt" (Ple\v{c}ko and Meinshausen, 2020), a different approach for mitigating unfairness by causally preprocessing data that uses quantile regression forests. With this, we show that our warping approach effectively identifies the most discriminated individuals and mitigates unfairness.

翻译：若平等个体得到平等对待，不平等个体得到不平等对待，则可定义该决策为公平决策。采用此定义后，设计用于减轻自动化决策系统中不公平性的机器学习模型时，在引入受保护属性时必须纳入因果思考：依据近期的一项提议，若个体在一个虚构的、规范意义上理想的（FiND）世界中是平等的，则我们将其定义为规范平等的个体；在该FiND世界中，受保护属性对目标变量没有（直接或间接的）因果效应。我们提出秩保持干预分布来定义一个满足此条件的特定FiND世界，并给出一种用于估计的扭曲方法。我们提出了针对该方法及其所得机器学习模型的评估标准，并通过仿真验证了其有效性。基于实证数据的实验展示了我们方法的实际应用，并将结果与"fairadapt"（Plečko与Meinshausen，2020）进行了比较——后者是一种通过因果预处理数据（使用分位数回归森林）来减轻不公平性的不同方法。由此，我们证明了我们的扭曲方法能有效识别受歧视最严重的个体并减轻不公平性。