Learning Controllable Fair Representations

by   Jiaming Song, et al.

Learning data representations that are transferable and fair with respect to certain protected attributes is crucial to reducing unfair decisions made downstream, while preserving the utility of the data. We propose an information-theoretically motivated objective for learning maximally expressive representations subject to fairness constraints. We demonstrate that a range of existing approaches optimize approximations to the Lagrangian dual of our objective. In contrast to these existing approaches, our objective provides the user control over the fairness of representations by specifying limits on unfairness. We introduce a dual optimization method that optimizes the model as well as the expressiveness-fairness trade-off. Empirical evidence suggests that our proposed method can account for multiple notions of fairness and achieves higher expressiveness at a lower computational cost.


page 1

page 2

page 3

page 4


Fair Ranking with Noisy Protected Attributes

The fair-ranking problem, which asks to rank a given set of items to max...

Paper Matching with Local Fairness Constraints

Automatically matching reviewers to papers is a crucial step of the peer...

Control Analysis of Packet Transmission Algorithms: Study on Fairness and Stability

This document is a study of fairness, feedback and stability notions of ...

Fair Representations by Compression

Organizations that collect and sell data face increasing scrutiny for th...

Addressing Fairness in Classification with a Model-Agnostic Multi-Objective Algorithm

The goal of fairness in classification is to learn a classifier that doe...

On Learning Fairness and Accuracy on Multiple Subgroups

We propose an analysis in fair learning that preserves the utility of th...

Computational Team Assembly with Fairness Constraints

Team assembly is a problem that demands trade-offs between multiple fair...

Code Repositories

Please sign up or login with your details

Forgot password? Click here to reset