Algorithmic Fairness, Institutional Logics, and Social Choice
Algorithmic Fairness, Institutional Logics, and Social Choice
复制标题
DOI：
--
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
R. Burke;A. Voida;Nicholas Mattei;Nasim Sonboli;Farzad Eskandanian
中科院分区：
文献类型：
--
作者：
R. Burke;A. Voida;Nicholas Mattei;Nasim Sonboli;Farzad Eskandanian
在机器学习研究中，公平性通常被认为是约束优化中的一种练习，基于预先确定的fiNed公平性度量。我们认为，这种抽象的算法公平模型与现实世界不太匹配，在现实世界中，应用程序可能嵌入到涉及多个类别的利益相关者以及多个社会和技术系统的更大背景中。我们可能会期待不同利益相关者围绕公平提出多项相互竞争的主张，特别是在面向社会公益的应用程序中。我们提出了计算社会选择作为一个有前景的框架来整合公平感知系统中关于系统结果的多个角度，并提供了一个应用于非专业fit的个性化推荐的例子。
Fairness, in machine learning research, is often conceived as an exercise in constrained optimization, based on a predefined fairness metric. We argue that this abstract model of algorithmic fairness is a poor match for the real world, in which applications are likely to be embedded within a larger context involving multiple classes of stakeholders as well as multiple social and technical systems. We may expect multiple, competing claims around fairness coming from various stakeholders, especially in applications oriented towards social good. We propose computational social choice as a promising framework for the integration of multiple perspectives on system outcomes in fairness-aware systems and provide an example in the application of personalized recommendation for a non-profit.