A growing body of literature in fairness-aware ML (fairML) aspires to mitigate machine learning (ML)-related unfairness in automated decision making (ADM) by defining metrics that measure fairness of an ML model and by proposing methods that ensure that trained ML models achieve low values in those measures. However, the underlying concept of fairness, i.e., the question of what fairness is, is rarely discussed, leaving a considerable gap between centuries of philosophical discussion and recent adoption of the concept in the ML community. In this work, we try to bridge this gap by formalizing a consistent concept of fairness and by translating the philosophical considerations into a formal framework for the training and evaluation of ML models in ADM systems. We derive that fairness problems can already arise without the presence of protected attributes, pointing out that fairness and predictive performance are not irreconcilable counterparts, but rather that the latter is necessary to achieve the former. Moreover, we argue why and how causal considerations are necessary when assessing fairness in the presence of protected attributes. We achieve greater linguistic clarity for the discussion of fairML and propose general algorithms for practical applications.

翻译：公平感知机器学习（fairML）领域日益增长的文献致力于通过定义衡量机器学习模型公平性的指标，并提出确保训练模型在这些指标上达到低值的方法，来缓解自动化决策（ADM）中与机器学习相关的不公平问题。然而，公平性的基本概念——即“公平是什么”这一问题——鲜少被讨论，导致数百年哲学讨论与机器学习社区近期对这一概念采纳之间存在显著鸿沟。本研究试图通过形式化一致的公平性概念，并将哲学思考转化为ADM系统中机器学习模型训练与评估的形式化框架，来弥合这一鸿沟。我们推导出，即使不存在受保护属性，公平性问题也可能出现，指出公平性与预测性能并非不可调和的对立面，相反，后者是实现前者的必要前提。此外，我们论证了在存在受保护属性时评估公平性为何及如何需要因果性思考。我们为fairML的讨论实现了更高的语言清晰度，并为实际应用提出了通用算法。