Generating Fair Universal Representations using Adversarial Models. (arXiv:1910.00411v7 [cs.LG] UPDATED)

Web: http://arxiv.org/abs/1910.00411

We present a data-driven framework for learning fair universal
representations (FUR) that guarantee statistical fairness for any learning task
that may not be known a priori. Our framework leverages recent advances in
adversarial learning to allow a data holder to learn representations in which a
set of sensitive attributes are decoupled from the rest of the dataset. We
formulate this as a constrained minimax game between an encoder and an
adversary where the constraint ensures a measure of usefulness (utility) …

arxiv models