Fair Representations by Compression

Authors

  • Xavier Gitiaux George Mason University
  • Huzefa Rangwala George Mason University

Keywords:

Bias, Fairness & Equity

Abstract

Organizations that collect and sell data face increasing scrutiny for the discriminatory use of data. We propose a novel unsupervised approach to map data into a compressed binary representation independent of sensitive attributes. We show that in an information bottleneck framework, a parsimonious representation should filter out information related to sensitive attributes if they are provided directly to the decoder. Empirical results show that the method achieves state-of-the-art accuracy-fairness trade-off and that explicit control of the entropy of the representation bit stream allows the user to move smoothly and simultaneously along both rate-distortion and rate-fairness curves.

Downloads

Published

2021-05-18

How to Cite

Gitiaux, X., & Rangwala, H. (2021). Fair Representations by Compression. Proceedings of the AAAI Conference on Artificial Intelligence, 35(13), 11506-11515. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17370

Issue

Section

AAAI Technical Track on Philosophy and Ethics of AI