Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations
arXiv: Learning, Volume abs/1707.00075, 2017.
How can we learn a classifier that is fair for a protected or sensitive group, when we do not know if the input to the classifier belongs to the protected group? How can we train such a classifier when data on the protected group is difficult to attain? In many settings, finding out the sensitive input attribute can be prohibitively expen...More
Full Text (Upload PDF)