Fairness-aware machine learning (fair-ml) techniques are algorithmic interventions designed to ensure that individuals who are affected by the predictions of a machine learning model are treated fairly, typically measured in terms of a quantitative fairness metric. Despite the multitude of fairness metrics and fair-ml algorithms, there is still little guidance on the suitability of different approaches in practice. In this paper, we present a framework for moral reasoning about the justification of fairness metrics and explore the moral implications of the use of fair-ml algorithms that optimize for them. In particular, we argue that whether a distribution of outcomes is fair, depends not only on the cause of inequalities but also on what moral claims decision subjects have to receive a particular benefit or avoid a burden. We use our framework to analyze the suitability of two fairness metrics under different circumstances. Subsequently, we explore moral arguments that support or reject the use of the fair-ml algorithm introduced by Hardt et al. (2016). We argue that under very specific circumstances, particular metrics correspond to a fair distribution of burdens and benefits. However, we also illustrate that enforcing a fairness metric by means of a fair-ml algorithm may not result in the fair distribution of outcomes and can have several undesirable side effects. We end with a call for a more holistic evaluation of fair-ml algorithms, beyond their direct optimization objectives.
翻译:公平理解机器学习(公平了解)技术是算法干预,旨在确保受到机器学习模型预测影响的个人得到公平对待,通常以量化公平度量衡量。尽管有多种公平度量和公平ml算法,但在实践中不同方法的适宜性仍然缺乏指导。在本文中,我们提出了一个道德推理框架,说明公平度量的正当性,并探讨使用对其最优化的公平ml算法的道德影响。特别是,我们争辩说,结果的分配是否公平,不仅取决于不平等的原因,还取决于道德索赔裁定主体必须获得特定利益或避免负担的道德索赔主体。我们利用我们的框架分析不同情况下两种公平度度量的合适性。随后,我们探讨支持或拒绝使用Hartt等人(2016年)提出的公平度量算法的道德推理。我们认为,在非常具体的情况下,特定度量法与公平负担和惠益的公平分配相符。然而,我们还可以说明,通过公平ml算法手段执行公平衡量公平度标准,其最终的结果可能不是公平的分配。