Characterizing Fairness Over the Set of Good Models Under Selective Labels

Characterizing Fairness Over the Set of Good Models Under Selective Labels
复制标题

在选择性标签下描述一组好模型的公平性

DOI:
--
复制
发表时间:
2021
期刊:
International Conference on Machine Learning
影响因子:
--
通讯作者:
A. Chouldechova
A. Chouldechova
中科院分区:
--
文献类型:
--
作者:
Amanda Coston;Ashesh Rambachan;A. Chouldechova

文献摘要

参考文献

被引文献

相似文献

在各种高风险环境中,生物风险评估被用来为决策提供信息。通常,多个预测模型提供相似的整体性能,但在个别情况下,它们的预测显着不同,这种经验现象被称为“罗生门效应”。“这些模型在不同的群体中可能具有不同的属性,因此具有不同的预测公平性。我们开发了一个框架,用于表征提供类似整体性能的模型集或“良好模型集”上的预测公平性。"我们的框架解决了在选择决策和结果不受观察到的数据特征影响的情况下选择性标记数据的经验相关挑战。我们的框架可用于1)用具有更好公平性的模型替换现有模型;或2)审计预测偏差。我们在现实世界的信用评分任务和累犯预测任务上说明了这些用例。
Algorithmic risk assessments are used to inform decisions in a wide variety of high-stakes settings. Often multiple predictive models deliver similar overall performance but differ markedly in their predictions for individual cases, an empirical phenomenon known as the"Rashomon Effect."These models may have different properties over various groups, and therefore have different predictive fairness properties. We develop a framework for characterizing predictive fairness properties over the set of models that deliver similar overall performance, or"the set of good models."Our framework addresses the empirically relevant challenge of selectively labelled data in the setting where the selection decision and outcome are unconfounded given the observed data features. Our framework can be used to 1) replace an existing model with one that has better fairness properties; or 2) audit for predictive bias. We illustrate these uses cases on a real-world credit-scoring task and a recidivism prediction task.
DOI: 10.1145/3442188.3445865
发表时间: 2019-11
期刊: Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency
影响因子: --
作者:
Harvineet Singh;Rina Singh;Vishwali Mhasawade;R. Chunara
通讯作者: Harvineet Singh;Rina Singh;Vishwali Mhasawade;R. Chunara
公平机器学习中来自偏见数据的残余不公平
DOI: --
发表时间: 2018
期刊: Proceedings of the 35th International Conference on Machine Learning
影响因子: --
作者:
Kallus, Nathan;Zhou, Angela
通讯作者: Zhou, Angela
DOI: 10.1016/j.jmrt.2023.02.141
发表时间: 2023-03-04
影响因子: 6.4
作者:
Wang, Qingjuan;He, Zeen;Yang, Congcong
通讯作者: Yang, Congcong