Machine learning fairness notions: Bridging the gap with real-world applications

Abstract

Fairness emerged as an important requirement to guarantee that Machine Learning (ML) predictive systems do not discriminate against specific individuals or entire sub-populations, in particular, minorities. Given the inherent subjectivity of viewing the concept of fairness, several notions of fairness have been introduced in the literature. This paper is a survey that illustrates the subtleties between fairness notions through a large number of examples and scenarios. In addition, unlike other surveys in the literature, it addresses the question of: which notion of fairness is most suited to a given real-world scenario and why? Our attempt to answer this question consists in (1) identifying the set of fairness-related characteristics of the real-world scenario at hand, (2) analyzing the behavior of each fairness notion, and then (3) fitting these two elements to recommend the most suitable fairness notion in every specific setup. The results are summarized in a decision diagram that can be used by practitioners and policymakers to navigate the relatively large catalog of ML.

References in corpus (18)

• Equality of Opportunity in Supervised Learning
• Counterfactual Fairness
• Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment
• The Measure and Mismeasure of Fairness
• Fairness Testing: Testing Software for Discrimination
• Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness
• Fairness Constraints: Mechanisms for Fair Classification
• Fairness in Machine Learning
• On the (im)possibility of fairness
• On Formalizing Fairness in Prediction with Machine Learning
• On the relation between accuracy and fairness in binary classification
• Fairness Through Computationally-Bounded Awareness
• A survey on measuring indirect discrimination in machine learning
• Fairness in Algorithmic Decision Making: An Excursion Through the Lens of Causality
• DAGER: Deep Age, Gender and Emotion Recognition Using Convolutional Neural Network
• Does mitigating ML's impact disparity require treatment disparity?
• PC-Fairness: A Unified Framework for Measuring Causality-based Fairness
• Probably Approximately Metric-Fair Learning

Cited by in corpus (3)

• Whither Bias Goes, I Will Go: An Integrative, Systematic Review of Algorithmic Bias Mitigation
• (Local) Differential Privacy has NO Disparate Impact on Fairness
• Toward Substantive Intersectional Algorithmic Fairness: Desiderata for a Feminist Approach