Spotlight Poster

Individual Arbitrariness and Group Fairness

Carol Long · Hsiang Hsu · Hsiang Hsu · Wael Alghamdi · Flavio Calmon

Great Hall & Hall B1+B2 (level 1) #1526
[ ] [ Project Page ]
Thu 14 Dec 8:45 a.m. PST — 10:45 a.m. PST

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.

Chat is not available.