Emergent Unfairness in Algorithmic Fairness-Accuracy Trade-Off Research

TL;DR

This paper critically examines the normative assumptions underlying fairness-accuracy trade-off research in machine learning, revealing that unexamined assumptions can lead to emergent unfairness and proposing a path for resolution.

Contribution

It highlights implicit normative assumptions in fairness-accuracy trade-off studies and discusses how these can cause unintended unfairness, offering a way to address this issue.

Findings

Implicit assumptions can lead to emergent unfairness

Current fairness measures may not capture all fairness aspects

Addressing normative assumptions can improve fairness outcomes

Abstract

Across machine learning (ML) sub-disciplines, researchers make explicit mathematical assumptions in order to facilitate proof-writing. We note that, specifically in the area of fairness-accuracy trade-off optimization scholarship, similar attention is not paid to the normative assumptions that ground this approach. Such assumptions presume that 1) accuracy and fairness are in inherent opposition to one another, 2) strict notions of mathematical equality can adequately model fairness, 3) it is possible to measure the accuracy and fairness of decisions independent from historical context, and 4) collecting more data on marginalized individuals is a reasonable solution to mitigate the effects of the trade-off. We argue that such assumptions, which are often left implicit and unexamined, lead to inconsistent conclusions: While the intended goal of this work may be to improve the fairness of machine learning models, these unexamined, implicit assumptions can in fact result in emergent unfairness. We conclude by suggesting a concrete path forward toward a potential resolution.