Automated decision systems are increasingly used to take consequential decisions in problems such as job hiring and loan granting with the hope of replacing subjective human decisions with objective machine learning (ML) algorithms. However, ML-based decision systems are prone to bias, which results in yet unfair decisions. Several notions of fairness have been defined in the literature to capture the different subtleties of this ethical and social concept (e.g., statistical parity, equal opportunity, etc.). Fairness requirements to be satisfied while learning models created several types of tensions among the different notions of fairness and other desirable properties such as privacy and classification accuracy. This paper surveys the commonly used fairness notions and discusses the tensions among them with privacy and accuracy. Different methods to address the fairness-accuracy trade-off (classified into four approaches, namely, pre-processing, in-processing, post-processing, and hybrid) are reviewed. The survey is consolidated with experimental analysis carried out on fairness benchmark datasets to illustrate the relationship between fairness measures and accuracy in real-world scenarios.

翻译：自动化决策系统越来越多地被用于处理诸如招聘和贷款审批等重大决策问题，旨在用客观的机器学习（ML）算法取代主观的人类决策。然而，基于ML的决策系统容易产生偏见，从而导致不公平的决策。为捕捉这一伦理与社会概念的不同细微之处，文献中定义了多种公平性概念（例如，统计均等、机会均等等）。在模型学习过程中需满足的公平性要求，引发了不同公平性概念之间以及与隐私和分类精度等其他理想属性之间的多种矛盾。本文综述了常用的公平性概念，并讨论了它们与隐私和精度之间的矛盾。文中回顾了解决公平性-精度权衡的不同方法（分为四类：预处理、处理中、后处理及混合方法）。该综述基于在公平性基准数据集上开展的实验分析，以阐明现实场景中公平性度量与精度之间的关系。