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. ML-based decision systems, however, are found to be prone to bias which result 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, but also with other desirable properties such as privacy and classification accuracy. This paper surveys the commonly used fairness notions and discusses the tensions that exist among them and 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 on real-world scenarios.
翻译:自动化决策系统越来越多地被用来在诸如招聘和发放贷款等问题上做出相应的决定,希望以客观的机器学习算法取代主观的人类决定;然而,基于ML的决策系统被认为容易产生偏向,导致不公平的决定;文献中界定了若干公平概念,以捕捉这一道德和社会概念的不同微妙之处(例如统计均等、机会均等等);在学习模式在不同公平概念之间造成几种类型的紧张关系,但也与其他可取的特性,如隐私和分类准确性之间造成紧张关系时,必须满足公平要求;本文调查了常用的公平概念,并讨论了这些概念之间存在的紧张关系以及隐私和准确性;审查了处理公平-准确性交易的不同方法(分为四种方法,即预处理、处理、后处理和混合方法);将调查与关于公平基准数据集的试验性分析结合起来,以说明公平措施与现实世界情景的准确性之间的关系。