Fair Learning with Private Demographic Data [article]

Hussein Mozannar, Mesrob I. Ohannessian, Nathan Srebro
2020 arXiv   pre-print
Sensitive attributes such as race are rarely available to learners in real world settings as their collection is often restricted by laws and regulations. We give a scheme that allows individuals to release their sensitive information privately while still allowing any downstream entity to learn non-discriminatory predictors. We show how to adapt non-discriminatory learners to work with privatized protected attributes giving theoretical guarantees on performance. Finally, we highlight how the
more » ... thodology could apply to learning fair predictors in settings where protected attributes are only available for a subset of the data.
arXiv:2002.11651v2 fatcat:pca5cyxhdzcszm5lnopw6vvdmu