Fairness in generative modeling

TL;DR

This paper introduces unsupervised fairness algorithms for generative models that do not require prior knowledge of sensitive variables, aiming to mitigate bias and mode collapse without using sensitive data.

Contribution

The authors propose general-purpose, unsupervised algorithms to improve fairness in generative modeling without relying on sensitive variable information.

Findings

Algorithms effectively address fairness issues in generative models.

Methods reduce mode collapse without sensitive data.

Applicable to various sensitive variables without prior knowledge.

Abstract

We design general-purpose algorithms for addressing fairness issues and mode collapse in generative modeling. More precisely, to design fair algorithms for as many sensitive variables as possible, including variables we might not be aware of, we assume no prior knowledge of sensitive variables: our algorithms use unsupervised fairness only, meaning no information related to the sensitive variables is used for our fairness-improving methods. All images of faces (even generated ones) have been removed to mitigate legal risks.