Flexibly Fair Representation Learning by Disentanglement

Elliot Creager, David Madras, Joern-Henrik Jacobsen, Marissa Weis, Kevin Swersky, Toniann Pitassi, Richard Zemel
Proceedings of the 36th International Conference on Machine Learning, PMLR 97:1436-1445, 2019.

Abstract

We consider the problem of learning representations that achieve group and subgroup fairness with respect to multiple sensitive attributes. Taking inspiration from the disentangled representation learning literature, we propose an algorithm for learning compact representations of datasets that are useful for reconstruction and prediction, but are also flexibly fair, meaning they can be easily modified at test time to achieve subgroup demographic parity with respect to multiple sensitive attributes and their conjunctions. We show empirically that the resulting encoder—which does not require the sensitive attributes for inference—allows for the adaptation of a single representation to a variety of fair classification tasks with new target labels and subgroup definitions.

Cite this Paper

BibTeX
@InProceedings{pmlr-v97-creager19a, title = {Flexibly Fair Representation Learning by Disentanglement}, author = {Creager, Elliot and Madras, David and Jacobsen, Joern-Henrik and Weis, Marissa and Swersky, Kevin and Pitassi, Toniann and Zemel, Richard}, booktitle = {Proceedings of the 36th International Conference on Machine Learning}, pages = {1436--1445}, year = {2019}, editor = {Chaudhuri, Kamalika and Salakhutdinov, Ruslan}, volume = {97}, series = {Proceedings of Machine Learning Research}, month = {09--15 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v97/creager19a/creager19a.pdf}, url = {https://proceedings.mlr.press/v97/creager19a.html}, abstract = {We consider the problem of learning representations that achieve group and subgroup fairness with respect to multiple sensitive attributes. Taking inspiration from the disentangled representation learning literature, we propose an algorithm for learning compact representations of datasets that are useful for reconstruction and prediction, but are also flexibly fair, meaning they can be easily modified at test time to achieve subgroup demographic parity with respect to multiple sensitive attributes and their conjunctions. We show empirically that the resulting encoder—which does not require the sensitive attributes for inference—allows for the adaptation of a single representation to a variety of fair classification tasks with new target labels and subgroup definitions.} }
Endnote
%0 Conference Paper %T Flexibly Fair Representation Learning by Disentanglement %A Elliot Creager %A David Madras %A Joern-Henrik Jacobsen %A Marissa Weis %A Kevin Swersky %A Toniann Pitassi %A Richard Zemel %B Proceedings of the 36th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2019 %E Kamalika Chaudhuri %E Ruslan Salakhutdinov %F pmlr-v97-creager19a %I PMLR %P 1436--1445 %U https://proceedings.mlr.press/v97/creager19a.html %V 97 %X We consider the problem of learning representations that achieve group and subgroup fairness with respect to multiple sensitive attributes. Taking inspiration from the disentangled representation learning literature, we propose an algorithm for learning compact representations of datasets that are useful for reconstruction and prediction, but are also flexibly fair, meaning they can be easily modified at test time to achieve subgroup demographic parity with respect to multiple sensitive attributes and their conjunctions. We show empirically that the resulting encoder—which does not require the sensitive attributes for inference—allows for the adaptation of a single representation to a variety of fair classification tasks with new target labels and subgroup definitions.
APA
Creager, E., Madras, D., Jacobsen, J., Weis, M., Swersky, K., Pitassi, T. & Zemel, R.. (2019). Flexibly Fair Representation Learning by Disentanglement. Proceedings of the 36th International Conference on Machine Learning, in Proceedings of Machine Learning Research 97:1436-1445 Available from https://proceedings.mlr.press/v97/creager19a.html.

Related Material