从功利主义到罗尔斯主义的算法公平性设计
From Utilitarian to Rawlsian Designs for Algorithmic Fairness
摘要：
关于如何衡量算法系统的“公平性”，文献中缺乏共识，不同的衡量标准往往不一致。在本文中，我们通过借鉴功利主义和罗尔斯的伦理框架来处理这一任务。非正式地说，这两种分配正义理论分别将“好”作为人口的效用总和或最坏结果来衡量。我们提出了一个参数化类的目标函数，这两个（可能）冲突的概念之间的“好”插值。这一类是表示放松罗尔斯的“面纱的服从”，其序列的最佳解决方案收敛到一个功利和罗尔斯的最佳。研究了该类的其他几个性质，包括：1）与正则化优化的关系，2）一致估计的可行性，以及3）算法成本。在几个现实世界的数据集，我们计算最优的解决方案，并构建功利主义和罗尔斯的“好”的概念之间的权衡。从经验上讲，我们证明，增加模型的复杂性可以表现出严格的改善这两个措施的“好”。这项工作表明，适当程度的“公平”可以通过设计师的偏好超过诱导功利主义和罗尔斯的“好”的空间。
英文摘要：
There is a lack of consensus within the literature as to how `fairness' of algorithmic systems can be measured, and different metrics can often be at odds. In this paper, we approach this task by drawing on the ethical frameworks of utilitarianism and John Rawls. Informally, these two theories of distributive justice measure the `good' as either a population's sum of utility, or worst-off outcomes, respectively. We present a parameterized class of objective functions that interpolates between these two (possibly) conflicting notions of the `good'. This class is shown to represent a relaxation of the Rawlsian `veil of ignorance', and its sequence of optimal solutions converges to both a utilitarian and Rawlsian optimum. Several other properties of this class are studied, including: 1) a relationship to regularized optimization, 2) feasibility of consistent estimation, and 3) algorithmic cost. In several real-world datasets, we compute optimal solutions and construct the tradeoff between utilitarian and Rawlsian notions of the `good'. Empirically, we demonstrate that increasing model complexity can manifest strict improvements to both measures of the `good'. This work suggests that the proper degree of `fairness' can be informed by a designer's preferences over the space of induced utilitarian and Rawlsian `good'.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
