Fairness in Machine Learning: A Survey

TL;DR

This survey reviews various approaches to fairness in machine learning, categorizing methods into pre-processing, in-processing, and post-processing, and discusses challenges across different learning tasks.

Contribution

It provides a comprehensive overview and organization of fairness mitigation techniques in machine learning, including diverse methods and open challenges.

Findings

Categorizes fairness approaches into three main stages.

Includes discussion on fairness in various learning paradigms.

Summarizes open challenges and dilemmas in fairness research.

Abstract

As Machine Learning technologies become increasingly used in contexts that affect citizens, companies as well as researchers need to be confident that their application of these methods will not have unexpected social implications, such as bias towards gender, ethnicity, and/or people with disabilities. There is significant literature on approaches to mitigate bias and promote fairness, yet the area is complex and hard to penetrate for newcomers to the domain. This article seeks to provide an overview of the different schools of thought and approaches to mitigating (social) biases and increase fairness in the Machine Learning literature. It organises approaches into the widely accepted framework of pre-processing, in-processing, and post-processing methods, subcategorizing into a further 11 method areas. Although much of the literature emphasizes binary classification, a discussion of fairness in regression, recommender systems, unsupervised learning, and natural language processing is also provided along with a selection of currently available open source libraries. The article concludes by summarising open challenges articulated as four dilemmas for fairness research.