As algorithmic prediction systems have become widespread, fears that these systems may inadvertently discriminate against members of underrepresented populations have grown. With the goal of understanding fundamental principles that underpin the growing number of approaches to mitigating algorithmic discrimination, we investigate the role of information in fair prediction. A common strategy for decision-making uses a predictor to assign individuals a risk score; then, individuals are selected or rejected on the basis of this score. In this work, we formalize a framework for measuring the information content of predictors. Central to this framework is the notion of a refinement; intuitively, a refinement of a predictor $z$ increases the overall informativeness of the predictions without losing the information already contained in $z$. We show that increasing information content through refinements improves the downstream selection rules across a wide range of fairness measures (e.g. true positive rates, false positive rates, selection rates). In turn, refinements provide a simple but effective tool for reducing disparity in treatment and impact without sacrificing the utility of the predictions. Our results suggest that in many applications, the perceived "cost of fairness" results from an information disparity across populations, and thus, may be avoided with improved information.
翻译:由于算法预测系统已变得十分普遍,人们担心这些系统可能无意中歧视代表性不足的人口成员,这种担心已经增加。为了了解支持越来越多的减轻算法歧视办法的基本原则,我们调查信息在公平预测中的作用。一个共同的决策战略使用预测器来分配个人的风险分数;然后,根据这一分数,个人被选中或被拒绝。在这项工作中,我们正式确定了一个衡量预测者信息内容的框架。这个框架的核心是改进概念;直觉地说,改进一个预测方美元可以提高预测的总体信息度,同时又不丧失已经以美元计算的信息。我们表明,通过改进,信息内容的增加可以改善一系列广泛的公平措施(如真正的正率、假正率、选择率)的下游选择规则。反过来,改进提供了一种简单而有效的工具,用以在不牺牲预测的效用的情况下减少治疗和影响的差距。我们的结果表明,在许多应用中,人们所认为的“公平性成本”来自人口之间的信息差异,因此,可以通过改进信息来避免。