On formalizing fairness in prediction with machine learning

By Pratik Gajane. 2017

223 citations recorded by the source corpus.

Machine learning algorithms for prediction are increasingly being used in critical decisions affecting human lives. Various fairness formalizations, with no firm consensus yet, are employed to prevent such algorithms from systematically discriminating against people based on certain attributes protected by law. The aim of this article is to survey how fairness is formalized in the machine learning literature for the task of prediction and present these formalizations with their corresponding notions of distributive justice from the social sciences literature. We provide theoretical as well as empirical critiques of these notions from the social sciences literature and explain how these critiques limit the suitability of the corresponding fairness formalizations to certain domains. We also suggest two notions of distributive justice which address some of these critiques and discuss avenues for prospective fairness formalizations.

Subfields: Artificial Intelligence, Safety Research, Sociology and Political Science, AI Ethics, Fairness & Society

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 Sociology and Political Science

In AI Ethics, Fairness & Society

Citations in the corpus

Prediction-Based Decisions and Fairness: A Catalogue of Choices, Assumptions, and Definitions (2018, background): “Fairness in ML has been explored in popular books [101, 37] and a White House report [99], surveyed in technical review papers [13, 41, 19], tutorials [9, 94, 92, 23], and an in-progress textbook [10], and inspired a number of software packages [129, 39, 45].”
Compositional Fairness Constraints for Graph Embeddings (2019, background): “There are many speciﬁc deﬁnitions of fairness, such as whether fairness refers to parity or satisfying certain preferences (see (Gajane & Pechenizkiy, 2017) for a detailed discussion).”
Counterfactual Fairness Is Basically Demographic Parity (2022, background): “Other inﬂuential work takes a similar position (Gajane and Pechenizkiy 2017; Corbett-Davies and Goel 2018; Coston et al. 2020).”
Machine Learning Testing: Survey, Landscapes and Horizons (2019, background): “There are several definitions of fairness proposed in the literature, yet no firm consensus [202], [203], [204], [205].”
Trustworthy Artificial Intelligence: A Review (2022, background): “Fairness definitions like fairness through awareness [57], fairness through unawareness [72], and counterfactual fairness [118] deal with individual fairness.”
A General Approach to Fairness with Optimal Transport (2020, background): “…learned models satisfy fairness properties (Dwork et al. 2012; Feldman et al. 2015; Goh et al. 2016; Chouldechova 2017; Corbett-Davies et al. 2017; Gajane and Pechenizkiy 2017; Kusner et al. 2017; Cotter et al. 2018; Mitchell, Potash, and Barocas 2018; Verma and Rubin 2018; Zhang and Bareinboim…”
The ethics of algorithms: key problems and solutions (2020, unknown): “Yet there remains a lack of agreement among researchers on the definition, measurements and standards of algorithmic fairness (Gajane and Pechenizkiy 2018; Saxena et al. 2019; Lee 2018; Milano et al. 2020).”
Fairness in Machine Learning (2020, background): “There exist several surveys that give an overview of current deﬁnitions and describe their relations (see e.g. [57, 130, 172]).”
Using satellite imagery to understand and promote sustainable development (2019, unknown): “While implementation of the guidelines certainly has its own challenges (106) (e.”
REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasets (2020, background): “, 2020) with varying definitions of fairness (Gajane and Pechenizkiy, 2017; Hardt et al., 2016; Kilbertus et al., 2017; Pleiss et al., 2017; Zhang et al., 2018) that are often deemed to be mathematically incompatible with each other (Chouldechova, 2017; Kleinberg et al.”
Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation (2019, background): “Various fairness criteria have been introduced and analyzed, including demographic parity [24, 51], predictive parity [15], error-rate balance [19], equality-of-odds and equality-of-opportunity [19], and fairness-through-unawareness [35] to try to quantify bias.”