论文标题
在顺序决策中实现长期公平性
Achieving Long-Term Fairness in Sequential Decision Making
论文作者
论文摘要
在本文中，我们提出了一个实现长期公平顺序决策的框架。通过进行硬干预措施，我们建议对时间滞后的因果图采取路径特异性影响，作为测量长期公平性的定量工具。然后将公平的顺序决策问题提出为效用的约束优化问题，作为目标，长期和短期公平性作为约束。我们表明，这种优化问题可以转换为表现性风险优化。最后，重复的风险最小化（RRM）用于模型训练，理论上分析了RRM的收敛性。经验评估显示了所提出的算法对合成和半合成时间数据集的有效性。
In this paper, we propose a framework for achieving long-term fair sequential decision making. By conducting both the hard and soft interventions, we propose to take path-specific effects on the time-lagged causal graph as a quantitative tool for measuring long-term fairness. The problem of fair sequential decision making is then formulated as a constrained optimization problem with the utility as the objective and the long-term and short-term fairness as constraints. We show that such an optimization problem can be converted to a performative risk optimization. Finally, repeated risk minimization (RRM) is used for model training, and the convergence of RRM is theoretically analyzed. The empirical evaluation shows the effectiveness of the proposed algorithm on synthetic and semi-synthetic temporal datasets.
