Fair Representations by Compression
Keywords:Bias, Fairness & Equity
AbstractOrganizations 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.
How to Cite
Gitiaux, X., & Rangwala, H. (2021). Fair Representations by Compression. Proceedings of the AAAI Conference on Artificial Intelligence, 35(13), 11506-11515. https://doi.org/10.1609/aaai.v35i13.17370
AAAI Technical Track on Philosophy and Ethics of AI