Arbitrariness Lies Beyond the Fairness-Accuracy Frontier

Author name not available (Why is that?)

Publication date: 15 June 2023

Abstract: Machine learning tasks may admit multiple competing models that achieve similar performance yet produce conflicting outputs for individual samples -- a phenomenon known as predictive multiplicity. We demonstrate that fairness interventions in machine learning optimized solely for group fairness and accuracy can exacerbate predictive multiplicity. Consequently, state-of-the-art fairness interventions can mask high predictive multiplicity behind favorable group fairness and accuracy metrics. We argue that a third axis of ``arbitrariness should be considered when deploying models to aid decision-making in applications of individual-level impact. To address this challenge, we propose an ensemble algorithm applicable to any fairness intervention that provably ensures more consistent predictions.

Has companion code repository: https://github.com/carol-long/fairness_and_arbitrariness

This page was built for publication: Arbitrariness Lies Beyond the Fairness-Accuracy Frontier

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6440465)