Flexibly Fair Representation Learning by Disentanglement
Elliot Creager · David Madras · Joern-Henrik Jacobsen · Marissa Weis · Kevin Swersky · Toniann Pitassi · Richard Zemel

Thu Jun 13th 11:25 -- 11:30 AM @ Seaside Ballroom

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---allows for the adaptation of a single representation to a variety of fair classification tasks with new target labels and subgroup definitions.

Author Information

Elliot Creager (University of Toronto)
David Madras (University of Toronto)
Jörn Jacobsen (Vector Institute and University of Toronto)
Marissa Weis (University of Tübingen)
Kevin Swersky (Google Brain)
Toniann Pitassi (University of Toronto)
Richard Zemel (Vector Institute)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors