Fair Representation Learning for Continuous Sensitive Attributes using Expectation of Integral Probability Metrics

TL;DR

This paper introduces a novel fair representation learning algorithm for continuous sensitive attributes using the Expectation of Integral Probability Metrics (EIPM), enabling fair predictions regardless of the prediction head.

Contribution

It extends fair representation learning to continuous sensitive attributes by proposing EIPM as a fairness measure and developing the FREM algorithm that outperforms baselines.

Findings

FREM achieves better fairness and accuracy than baseline methods.

EIPM can be accurately estimated with finite samples.

The approach applies to continuous sensitive attributes like age and income.

Abstract

AI fairness, also known as algorithmic fairness, aims to ensure that algorithms operate without bias or discrimination towards any individual or group. Among various AI algorithms, the Fair Representation Learning (FRL) approach has gained significant interest in recent years. However, existing FRL algorithms have a limitation: they are primarily designed for categorical sensitive attributes and thus cannot be applied to continuous sensitive attributes, such as age or income. In this paper, we propose an FRL algorithm for continuous sensitive attributes. First, we introduce a measure called the Expectation of Integral Probability Metrics (EIPM) to assess the fairness level of representation space for continuous sensitive attributes. We demonstrate that if the distribution of the representation has a low EIPM value, then any prediction head constructed on the top of the representation become fair, regardless of the selection of the prediction head. Furthermore, EIPM possesses a distinguished advantage in that it can be accurately estimated using our proposed estimator with finite samples. Based on these properties, we propose a new FRL algorithm called Fair Representation using EIPM with MMD (FREM). Experimental evidences show that FREM outperforms other baseline methods.