Uncertainty in Fairness Assessment: Maintaining Stable Conclusions Despite Fluctuations

TL;DR

This paper introduces the Uncertainty Matters (UM) framework, a Bayesian approach that provides stable and informative assessments of fairness and performance metrics across demographic groups, even under data fluctuations.

Contribution

The paper generalizes a Bayesian Beta-Binomial approach to derive posterior distributions for fairness metrics, extending it to K-fold cross-validation for more reliable evaluations.

Findings

UM offers more stable fairness assessments than classical methods.

UM provides more informative metrics with reduced variance.

Experiments demonstrate improved stability and informativeness of UM.

Abstract

Several recent works encourage the use of a Bayesian framework when assessing performance and fairness metrics of a classification algorithm in a supervised setting. We propose the Uncertainty Matters (UM) framework that generalizes a Beta-Binomial approach to derive the posterior distribution of any criteria combination, allowing stable performance assessment in a bias-aware setting.We suggest modeling the confusion matrix of each demographic group using a Multinomial distribution updated through a Bayesian procedure. We extend UM to be applicable under the popular K-fold cross-validation procedure. Experiments highlight the benefits of UM over classical evaluation frameworks regarding informativeness and stability.