Fairness with Overlapping Groups
This work addresses algorithmic fairness for overlapping demographic groups, offering a foundational approach that is incremental in unifying and extending prior methods.
The paper tackles the problem of ensuring fairness across overlapping groups in classification by deriving the Bayes-optimal classifier through probabilistic population analysis, which unifies existing methods and extends to various metrics, outperforming baselines on real datasets in fairness-performance tradeoffs.
In algorithmically fair prediction problems, a standard goal is to ensure the equality of fairness metrics across multiple overlapping groups simultaneously. We reconsider this standard fair classification problem using a probabilistic population analysis, which, in turn, reveals the Bayes-optimal classifier. Our approach unifies a variety of existing group-fair classification methods and enables extensions to a wide range of non-decomposable multiclass performance metrics and fairness measures. The Bayes-optimal classifier further inspires consistent procedures for algorithmically fair classification with overlapping groups. On a variety of real datasets, the proposed approach outperforms baselines in terms of its fairness-performance tradeoff.