Fairness in Machine Learning: A Survey

By Simon Caton, Christian Haas. 2020

916 citations recorded by the source corpus.

When Machine Learning technologies are used in contexts that affect citizens, companies as well as researchers need to be confident that there will not be any 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 that aim to increase the fairness of Machine Learning. It organizes 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, and unsupervised learning is also provided along with a selection of currently available open source libraries. The article concludes by summarizing open challenges articulated as five dilemmas for fairness research.

Subfields: Artificial Intelligence, Safety Research, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Safety Research

In Safety, Robustness & Interpretability

Citations in the corpus

On The Impact of Machine Learning Randomness on Group Fairness (2023, background): “Understanding these biases and the resulting ethical obligations have led to the rise of fair machine learning research [13, 15, 37].”
Algorithm fairness in artificial intelligence for medicine and healthcare (2023, background): “…because protected health information may include sensitive attributes, such as race and gender, and because data-generating processes across healthcare systems are heterogeneous and often capture different patient demographics, causing data mismatches in model development and deployment 21 .”
AUC Maximization in the Era of Big Data and AI: A Survey (2022, background): “Two issues are of foremost importance, namely fairness [7, 10, 20, 113] and interpretability [3, 24, 64].”
Counterfactual Fairness Is Basically Demographic Parity (2022, background): “For example, in (Caton and Haas 2020), they note that demographic parity is ﬂawed because it does not account for potential differences between groups, but do not mention limitations of counterfactual fairness.”
A Survey on the Fairness of Recommender Systems (2022, background): “[14, 63] concentrate on fairness in machine learning, but fairness in recommendation is not covered, especially its unique characteristics.”
Trustworthy AI: From Principles to Practices (2021, methodology): “Fairness can be applicable at multiple granularities of system behavior [66, 242, 339].”