Multiaccurate Proxies for Downstream Fairness

Multiaccurate Proxies for Downstream Fairness
复制标题

下游公平性的多准确代理

DOI:
10.1145/3531146.3533180
复制
发表时间:
2021
期刊:
Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency
影响因子:
--
通讯作者:
Saeed Sharifi
Saeed Sharifi
中科院分区:
--
文献类型:
--
作者:
Emily Diana;Wesley Gill;Michael Kearns;K. Kenthapadi;Aaron Roth;Saeed Sharifi

文献摘要

参考文献

被引文献

相似文献

我们研究训练一个模型的问题,该模型在训练时间不可用时必须遵守人口公平的条件 - 换句话说,当我们没有有关种族数据的数据时,我们如何训练模型以公平的种族公平?我们采用了公平的管道观点,其中确实可以访问敏感功能的“上游”学习者将从其他属性中学习这些功能的代理模型。在其预测任务上的最小假设 - 能够使用代理来训练与真实敏感功能相对于下游模型类别的多级敏感功能的模型。 - 学习代理和进行实验评估的甲骨文有效算法和概括范围。
We study the problem of training a model that must obey demographic fairness conditions when the sensitive features are not available at training time — in other words, how can we train a model to be fair by race when we don’t have data about race? We adopt a fairness pipeline perspective, in which an “upstream” learner that does have access to the sensitive features will learn a proxy model for these features from the other attributes. The goal of the proxy is to allow a general “downstream” learner — with minimal assumptions on their prediction task — to be able to use the proxy to train a model that is fair with respect to the true sensitive features. We show that obeying multiaccuracy constraints with respect to the downstream model class suffices for this purpose, provide sample- and oracle efficient-algorithms and generalization bounds for learning such proxies, and conduct an experimental evaluation. In general, multiaccuracy is much easier to satisfy than classification accuracy, and can be satisfied even when the sensitive features are hard to predict.
DOI: --
发表时间: 2018-07
期刊: --
影响因子: --
作者:
Úrsula Hébert-Johnson;Michael P. Kim;Omer Reingold;G. Rothblum
通讯作者: Úrsula Hébert-Johnson;Michael P. Kim;Omer Reingold;G. Rothblum
DOI: --
发表时间: 2020-07
期刊: Proceedings of machine learning research
影响因子: --
作者:
Natalia Martínez;Martín Bertrán;G. Sapiro
通讯作者: Natalia Martínez;Martín Bertrán;G. Sapiro
管道中的个人公平性
DOI: --
发表时间: 2020
影响因子: --
作者:
Dwork, C;Ilvento, C;Jagadeesan, M
通讯作者: Jagadeesan, M
DOI: --
发表时间: 2021-08
期刊: --
影响因子: --
作者:
Frances Ding;Moritz Hardt;John Miller;Ludwig Schmidt
通讯作者: Frances Ding;Moritz Hardt;John Miller;Ludwig Schmidt
DOI: 10.1016/j.optlastec.2013.04.024
发表时间: 2013-12-01
影响因子: 5
作者:
Cong, Dalong;Zhou, Hong;Wang, Chuanwei
通讯作者: Wang, Chuanwei