Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations

    arXiv: Learning, Volume abs/1707.00075, 2017.

    Cited by: 20|Bibtex|Views21|Links
    EI

    Abstract:

    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

    Code:

    Data:

    Your rating :
    0

     

    Tags
    Comments