Timezone: »

Exploiting MMD and Sinkhorn Divergences for Fair and Transferable Representation Learning
Luca Oneto · Michele Donini · Giulia Luise · Carlo Ciliberto · Andreas Maurer · Massimiliano Pontil

Wed Dec 09 09:00 AM -- 11:00 AM (PST) @ Poster Session 3 #868

Developing learning methods which do not discriminate subgroups in the population is a central goal of algorithmic fairness. One way to reach this goal is by modifying the data representation in order to meet certain fairness constraints. In this work we measure fairness according to demographic parity. This requires the probability of the possible model decisions to be independent of the sensitive information. We argue that the goal of imposing demographic parity can be substantially facilitated within a multitask learning setting. We present a method for learning a shared fair representation across multiple tasks, by means of different new constraints based on MMD and Sinkhorn Divergences. We derive learning bounds establishing that the learned representation transfers well to novel tasks. We present experiments on three real world datasets, showing that the proposed method outperforms state-of-the-art approaches by a significant margin.

Author Information

Luca Oneto (University of Genoa)
Michele Donini (Amazon)
Giulia Luise (University College London)
Carlo Ciliberto (Imperial College London)
Andreas Maurer
Massimiliano Pontil (IIT)

More from the Same Authors