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 \emph{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---enables the adaptation of a single representation to a variety of fair classification tasks with new target labels and subgroup definitions.
@article{arxiv.1906.02589,
title = {Flexibly Fair Representation Learning by Disentanglement},
author = {Elliot Creager and David Madras and Jörn-Henrik Jacobsen and Marissa A. Weis and Kevin Swersky and Toniann Pitassi and Richard Zemel},
journal= {arXiv preprint arXiv:1906.02589},
year = {2019}
}