More Like this

1. The measure and mismeasure of fairness

   Corbett-Davies, Sam; Gaebler, Johann D.; Nilforoshan, Hamed; Shroff, Ravi; Goel, Sharad (August 2023, Journal of machine learning research)

   Weinberger, Kilian (Ed.)

   The field of fair machine learning aims to ensure that decisions guided by algorithms are equitable. Over the last decade, several formal, mathematical definitions of fairness have gained prominence. Here we first assemble and categorize these definitions into two broad families: (1) those that constrain the effects of decisions on disparities; and (2) those that constrain the effects of legally protected characteristics, like race and gender, on decisions. We then show, analytically and empirically, that both families of definitions typically result in strongly Pareto dominated decision policies. For example, in the case of college admissions, adhering to popular formal conceptions of fairness would simultaneously result in lower student-body diversity and a less academically prepared class, relative to what one could achieve by explicitly tailoring admissions policies to achieve desired outcomes. In this sense, requiring that these fairness definitions hold can, perversely, harm the very groups they were designed to protect. In contrast to axiomatic notions of fairness, we argue that the equitable design of algorithms requires grappling with their context-specific consequences, akin to the equitable design of policy. We conclude by listing several open challenges in fair machine learning and offering strategies to ensure algorithms are better aligned with policy goals. 

   more » « less
2. Causal Conceptions of Fairness and their Consequences

   Nilforoshan, Hamed; Gaebler, Johann D.; Shroff, Ravi; Goel, Sharad (January 2022, Proceedings of the 39th International Conference on Machine Learning)

   Chaudhuri, Kamalika; Jegelka, Stefanie; Song, Le; Szepesvari, Csaba; Niu, Gang; Sabato, Sivan (Ed.)

   Recent work highlights the role of causality in designing equitable decision-making algorithms. It is not immediately clear, however, how existing causal conceptions of fairness relate to one another, or what the consequences are of using these definitions as design principles. Here, we first assemble and categorize popular causal definitions of algorithmic fairness into two broad families: (1) those that constrain the effects of decisions on counterfactual disparities; and (2) those that constrain the effects of legally protected characteristics, like race and gender, on decisions. We then show, analytically and empirically, that both families of definitions almost always—in a measure theoretic sense—result in strongly Pareto dominated decision policies, meaning there is an alternative, unconstrained policy favored by every stakeholder with preferences drawn from a large, natural class. For example, in the case of college admissions decisions, policies constrained to satisfy causal fairness definitions would be disfavored by every stakeholder with neutral or positive preferences for both academic preparedness and diversity. Indeed, under a prominent definition of causal fairness, we prove the resulting policies require admitting all students with the same probability, regardless of academic qualifications or group membership. Our results highlight formal limitations and potential adverse consequences of common mathematical notions of causal fairness. 

   more » « less
3. Measuring Racial Discrimination in Algorithms

   https://doi.org/10.1257/pandp.20211080  

   Arnold, David; Dobbie, Will; Hull, Peter (May 2021, AEA Papers and Proceedings)

   Algorithmic decision-making can lead to discrimination against legally protected groups, but measuring such discrimination is often hampered by a fundamental selection challenge. We develop new quasi-experimental tools to overcome this challenge and measure algorithmic discrimination in pretrial bail decisions. We show that the selection challenge reduces to the challenge of measuring four moments, which can be estimated by extrapolating quasi-experimental variation across as-good-as-randomly assigned decision-makers. Estimates from New York City show that both a sophisticated machine learning algorithm and a simpler regression model discriminate against Black defendants even though defendant race and ethnicity are not included in the training data. 

   more » « less
4. Keeping Community in the Loop: Understanding Wikipedia Stakeholder Values for Machine Learning-Based Systems

   https://doi.org/10.1145/3313831.3376783  

   Smith, C. Estelle; Yu, Bowen; Srivastava, Anjali; Halfaker, Aaron; Terveen, Loren; Zhu, Haiyi (April 2020, Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems)

   On Wikipedia, sophisticated algorithmic tools are used to assess the quality of edits and take corrective actions. However, algorithms can fail to solve the problems they were designed for if they conflict with the values of communities who use them. In this study, we take a Value-Sensitive Algorithm Design approach to understanding a community-created and -maintained machine learning-based algorithm called the Objective Revision Evaluation System (ORES)---a quality prediction system used in numerous Wikipedia applications and contexts. Five major values converged across stakeholder groups that ORES (and its dependent applications) should: (1) reduce the effort of community maintenance, (2) maintain human judgement as the final authority, (3) support differing peoples' differing workflows, (4) encourage positive engagement with diverse editor groups, and (5) establish trustworthiness of people and algorithms within the community. We reveal tensions between these values and discuss implications for future research to improve algorithms like ORES. 

   more » « less
5. Counterfactual Fairness Is Basically Demographic Parity

   https://doi.org/10.1609/aaai.v37i12.26691  

   Rosenblatt, Lucas; Witter, R Teal (June 2023, Proceedings of the AAAI Conference on Artificial Intelligence)

   Making fair decisions is crucial to ethically implementing machine learning algorithms in social settings. In this work, we consider the celebrated definition of counterfactual fairness. We begin by showing that an algorithm which satisfies counterfactual fairness also satisfies demographic parity, a far simpler fairness constraint. Similarly, we show that all algorithms satisfying demographic parity can be trivially modified to satisfy counterfactual fairness. Together, our results indicate that counterfactual fairness is basically equivalent to demographic parity, which has important implications for the growing body of work on counterfactual fairness. We then validate our theoretical findings empirically, analyzing three existing algorithms for counterfactual fairness against three simple benchmarks. We find that two simple benchmark algorithms outperform all three existing algorithms---in terms of fairness, accuracy, and efficiency---on several data sets. Our analysis leads us to formalize a concrete fairness goal: to preserve the order of individuals within protected groups. We believe transparency around the ordering of individuals within protected groups makes fair algorithms more trustworthy. By design, the two simple benchmark algorithms satisfy this goal while the existing algorithms do not. 

   more » « less