Learning Fair Representations via Rate-Distortion Maximization

Text representations learned by machine learning models often encode undesirable demographic information of the user. Predictive models based on these representations can rely on such information resulting in biased decisions. We present a novel debiasing technique Fairness-aware Rate Maximization (FaRM), that removes demographic information by making representations of instances belonging to the same protected attribute class uncorrelated using the rate-distortion function. FaRM is able to debias representations with or without a target task at hand. FaRM can also be adapted to simultaneously remove information about multiple protected attributes. Empirical evaluations show that FaRM achieves state-of-the-art performance on several datasets, and learned representations leak significantly less protected attribute information against an attack by a non-linear probing network.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/25/2022

Sustaining Fairness via Incremental Learning

Machine learning systems are often deployed for making critical decision...
research
04/27/2023

FLAC: Fairness-Aware Representation Learning by Suppressing Attribute-Class Associations

Bias in computer vision systems can perpetuate or even amplify discrimin...
research
09/22/2021

Contrastive Learning for Fair Representations

Trained classification models can unintentionally lead to biased represe...
research
02/06/2023

Erasure of Unaligned Attributes from Neural Representations

We present the Assignment-Maximization Spectral Attribute removaL (AMSAL...
research
04/27/2021

Multi-Fair Pareto Boosting

Fairness-aware machine learning for multiple protected at-tributes (refe...
research
05/28/2021

Fair Representations by Compression

Organizations that collect and sell data face increasing scrutiny for th...
research
07/24/2023

Causal Fair Machine Learning via Rank-Preserving Interventional Distributions

A decision can be defined as fair if equal individuals are treated equal...

Please sign up or login with your details

Forgot password? Click here to reset