A Clarification of the Nuances in the Fairness Metrics Landscape

TL;DR

This paper clarifies the complex landscape of fairness metrics in machine learning, analyzing their differences, implications, and relationships to better understand their application in AI decision-making.

Contribution

It provides a systematic analysis of various fairness definitions, highlighting their nuances, differences, and the orthogonality among them to organize the existing landscape.

Findings

Clarifies distinctions between fairness notions

Analyzes implications of different fairness metrics

Provides a structured overview of fairness landscape

Abstract

In recent years, the problem of addressing fairness in Machine Learning (ML) and automatic decision-making has attracted a lot of attention in the scientific communities dealing with Artificial Intelligence. A plethora of different definitions of fairness in ML have been proposed, that consider different notions of what is a "fair decision" in situations impacting individuals in the population. The precise differences, implications and "orthogonality" between these notions have not yet been fully analyzed in the literature. In this work, we try to make some order out of this zoo of definitions.