Arbitrariness Lies Beyond the Fairness-Accuracy Frontier

TL;DR

This paper highlights that optimizing for fairness and accuracy in machine learning can increase predictive multiplicity, and proposes an ensemble method to improve consistency across models.

Contribution

It introduces the concept of arbitrariness as a third axis in model evaluation and provides an ensemble algorithm to reduce predictive multiplicity.

Findings

Fairness interventions can increase predictive multiplicity.

Ensemble methods can improve prediction consistency.

Current fairness metrics may mask underlying model variability.

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.