Emergent Unfairness in Algorithmic Fairness-Accuracy Trade-Off Research
This work addresses a foundational problem in ML fairness research, highlighting how unexamined assumptions can undermine fairness goals, making it significant for researchers and practitioners in ethical AI.
The paper critiques the implicit normative assumptions in algorithmic fairness-accuracy trade-off research, arguing they lead to emergent unfairness despite aiming to improve fairness, and suggests a path forward for resolution.
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.