The use of algorithmic (learning-based) decision making in scenarios that affect human lives has motivated a number of recent studies to investigate such decision making systems for potential unfairness, such as discrimination against subjects based on their sensitive features like gender or race. However, when judging the fairness of a newly designed decision making system, these studies have overlooked an important influence on people's perceptions of fairness, which is how the new algorithm changes the status quo, i.e., decisions of the existing decision making system. Motivated by extensive literature in behavioral economics and behavioral psychology (prospect theory), we propose a notion of fair updates that we refer to as loss-averse updates. Loss-averse updates constrain the updates to yield improved (more beneficial) outcomes to subjects compared to the status quo. We propose tractable proxy measures that would allow this notion to be incorporated in the training of a variety of linear and non-linear classifiers. We show how our proxy measures can be combined with existing measures for training nondiscriminatory classifiers. Our evaluation using synthetic and real-world datasets demonstrates that the proposed proxy measures are effective for their desired tasks.
翻译:在影响人类生活的情景中,利用算法(基于学习)决策方法,促使最近进行了一系列研究,调查这种决策系统的潜在不公平性,例如基于性别或种族等敏感特征的歧视,但是,在判断新设计的决策系统是否公平时,这些研究忽视了对人们公平感的重要影响,即新的算法如何改变现状,即现有决策系统的决定。我们受到行为经济学和行为心理学(前景理论)大量文献的激励,提出了公平更新的概念,我们称之为逆损失更新。反损失更新限制了更新,使更新与现状相比,对主题产生更好的(更有益的)结果。我们提出了可移动的代用措施,使这一概念被纳入各种线性和非线性分类人员的培训中。我们展示了我们的代用措施如何与培训不歧视分类人员的现有措施相结合。我们使用合成和真实世界数据集进行的评估表明,拟议的代用措施对于他们所期望的任务是有效的。