论文标题
基于学习的顺序决策算法公平：调查
Fairness in Learning-Based Sequential Decision Algorithms: A Survey
论文作者
论文摘要
在静态环境中已经对决策中的算法公平性进行了广泛的研究，在静态环境中，对分类等任务进行了一声决策。但是，实际上，大多数决策过程具有顺序性质，过去做出的决策可能会对未来的数据产生影响。当决策影响个人或用户生成用于未来决策的数据时，情况尤其如此。在这项调查中，我们回顾了有关数据驱动的顺序决策公平性的现有文献。我们将重点介绍两种顺序决策：（1）过去的决策对基本用户群体没有影响，因此对未来数据没有影响； （2）过去的决策会影响潜在的用户群体以及未来的数据，这可能会影响未来的决策。在每种情况下，都检查了各种公平干预措施对基础人群的影响。
Algorithmic fairness in decision-making has been studied extensively in static settings where one-shot decisions are made on tasks such as classification. However, in practice most decision-making processes are of a sequential nature, where decisions made in the past may have an impact on future data. This is particularly the case when decisions affect the individuals or users generating the data used for future decisions. In this survey, we review existing literature on the fairness of data-driven sequential decision-making. We will focus on two types of sequential decisions: (1) past decisions have no impact on the underlying user population and thus no impact on future data; (2) past decisions have an impact on the underlying user population and therefore the future data, which can then impact future decisions. In each case the impact of various fairness interventions on the underlying population is examined.
