Learning Adversarially Fair and Transferable Representations

David Madras, Elliot Creager, Toniann Pitassi, Richard Zemel
Proceedings of the 35th International Conference on Machine Learning, PMLR 80:3384-3393, 2018.

Abstract

In this paper, we advocate for representation learning as the key to mitigating unfair prediction outcomes downstream. Motivated by a scenario where learned representations are used by third parties with unknown objectives, we propose and explore adversarial representation learning as a natural method of ensuring those parties act fairly. We connect group fairness (demographic parity, equalized odds, and equal opportunity) to different adversarial objectives. Through worst-case theoretical guarantees and experimental validation, we show that the choice of this objective is crucial to fair prediction. Furthermore, we present the first in-depth experimental demonstration of fair transfer learning and demonstrate empirically that our learned representations admit fair predictions on new tasks while maintaining utility, an essential goal of fair representation learning.

Cite this Paper

BibTeX
@InProceedings{pmlr-v80-madras18a, title = {Learning Adversarially Fair and Transferable Representations}, author = {Madras, David and Creager, Elliot and Pitassi, Toniann and Zemel, Richard}, booktitle = {Proceedings of the 35th International Conference on Machine Learning}, pages = {3384--3393}, year = {2018}, editor = {Dy, Jennifer and Krause, Andreas}, volume = {80}, series = {Proceedings of Machine Learning Research}, month = {10--15 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v80/madras18a/madras18a.pdf}, url = {https://proceedings.mlr.press/v80/madras18a.html}, abstract = {In this paper, we advocate for representation learning as the key to mitigating unfair prediction outcomes downstream. Motivated by a scenario where learned representations are used by third parties with unknown objectives, we propose and explore adversarial representation learning as a natural method of ensuring those parties act fairly. We connect group fairness (demographic parity, equalized odds, and equal opportunity) to different adversarial objectives. Through worst-case theoretical guarantees and experimental validation, we show that the choice of this objective is crucial to fair prediction. Furthermore, we present the first in-depth experimental demonstration of fair transfer learning and demonstrate empirically that our learned representations admit fair predictions on new tasks while maintaining utility, an essential goal of fair representation learning.} }
Endnote
%0 Conference Paper %T Learning Adversarially Fair and Transferable Representations %A David Madras %A Elliot Creager %A Toniann Pitassi %A Richard Zemel %B Proceedings of the 35th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2018 %E Jennifer Dy %E Andreas Krause %F pmlr-v80-madras18a %I PMLR %P 3384--3393 %U https://proceedings.mlr.press/v80/madras18a.html %V 80 %X In this paper, we advocate for representation learning as the key to mitigating unfair prediction outcomes downstream. Motivated by a scenario where learned representations are used by third parties with unknown objectives, we propose and explore adversarial representation learning as a natural method of ensuring those parties act fairly. We connect group fairness (demographic parity, equalized odds, and equal opportunity) to different adversarial objectives. Through worst-case theoretical guarantees and experimental validation, we show that the choice of this objective is crucial to fair prediction. Furthermore, we present the first in-depth experimental demonstration of fair transfer learning and demonstrate empirically that our learned representations admit fair predictions on new tasks while maintaining utility, an essential goal of fair representation learning.
APA
Madras, D., Creager, E., Pitassi, T. & Zemel, R.. (2018). Learning Adversarially Fair and Transferable Representations. Proceedings of the 35th International Conference on Machine Learning, in Proceedings of Machine Learning Research 80:3384-3393 Available from https://proceedings.mlr.press/v80/madras18a.html.

Related Material