论文标题
人类和算法决策的主要公平性
Principal Fairness for Human and Algorithmic Decision-Making
论文作者
论文摘要
利用因果推论文献中主要分层的概念，我们引入了一种新的公平概念，称为主要公平，人类和算法决策。关键的想法是，不应区分会受到同样影响决定的个人。与现有的公平统计定义不同，主要公平性明确说明了个人可以受到决定影响的事实。此外，我们解释了主要公平与现有基于因果关系的公平标准的不同。例如，与反事实公平标准相反，主要公平考虑了有关决定的影响，而不是受保护的属性的效果。我们简要讨论如何在拟议的主要公平标准下处理经验评估和政策学习问题。
Using the concept of principal stratification from the causal inference literature, we introduce a new notion of fairness, called principal fairness, for human and algorithmic decision-making. The key idea is that one should not discriminate among individuals who would be similarly affected by the decision. Unlike the existing statistical definitions of fairness, principal fairness explicitly accounts for the fact that individuals can be impacted by the decision. Furthermore, we explain how principal fairness differs from the existing causality-based fairness criteria. In contrast to the counterfactual fairness criteria, for example, principal fairness considers the effects of decision in question rather than those of protected attributes of interest. We briefly discuss how to approach empirical evaluation and policy learning problems under the proposed principal fairness criterion.
