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:
影响因子:
--
通讯作者:
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
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.
登录
查看更多内容
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
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
影响因子:
5
作者:
Cong, Dalong;Zhou, Hong;Wang, Chuanwei
通讯作者:
Wang, Chuanwei