Mathematical Notions vs. Human Perception of Fairness: A Descriptive Approach to Fairness for Machine Learning

Abstract

Fairness for Machine Learning has received considerable attention, recently. Various mathematical formulations of fairness have been proposed, and it has been shown that it is impossible to satisfy all of them simultaneously. The literature so far has dealt with these impossibility results by quantifying the tradeoffs between different formulations of fairness. Our work takes a different perspective on this issue. Rather than requiring all notions of fairness to (partially) hold at the same time, we ask which one of them is the most appropriate given the societal domain in which the decision-making model is to be deployed. We take a descriptive approach and set out to identify the notion of fairness that best captures lay people's perception of fairness. We run adaptive experiments designed to pinpoint the most compatible notion of fairness with each participant's choices through a small number of tests. Perhaps surprisingly, we find that the most simplistic mathematical definition of fairness-namely, demographic parity-most closely matches people's idea of fairness in two distinct application scenarios. This conclusion remains intact even when we explicitly tell the participants about the alternative, more complicated definitions of fairness, and we reduce the cognitive burden of evaluating those notions for them. Our findings have important implications for the Fair ML literature and the discourse on formalizing algorithmic fairness.

Human Perceptions on Moral Responsibility of AI: A Case Study in AI-Assisted Bail Decision-Making

“…For instance, Lee et al studied people's perception of trust, fairness, and justice in the context of algorithmic decision-making [56,57] and proposed how to embed these views into a policymaking framework [58]. Other scholars explored people's perceptions of procedural [41] and distributive [84,90] aspects of algorithmic fairness and studied how they relate to individual differences [42,76,108]. Nonetheless, little attention is paid to the public attribution of (moral) responsibility to stakeholders (e.g., [43,56,81]), particularly the prospect of responsibility ascription to the AI system per se.…”

CheXclusion: Fairness gaps in deep chest X-ray classifiers

“…There are several conflicting definitions of fairness, many of which are not simultaneously achievable [23]. The appropriate choice of a disparity metric is generally task dependent, but balancing error rates between different subgroups in a common consideration [8,17], with equal accuracy across subgroups being a popular choice in medical settings [42]. In this work we will consider the equality of opportunity notion of fairness and evaluate the rate of correct diagnosis in sick members of different attributes as well as missdiagnosis rate with no disease.…”

The Challenge of Imputation in Explainable Artificial Intelligence Models

“…An important axis of accountability of Artificial Intelligence systems is Fairness. There are multiple notions of what constitutes fairness in machine learning [15], to illustrate the effect of imputation on fairness and explainability we focus on group level notions of fairness. A system that is fair need not be explainable if the underlying algorithm can ensure that the various groups of interest are being scored in a fair manner even when the model is blackbox.…”