Algorithmic Fairness from a Non-ideal Perspective
Open accessThe DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.
Abstract
Inspired by recent breakthroughs in predictive modeling, practitioners in both industry and government have turned to machine learning with hopes of operationalizing predictions to drive automated decisions. Unfortunately, many social desiderata concerning consequential decisions, such as justice or fairness, have no natural formulation within a purely predictive framework. In the hopes of mitigating these problems, researchers have proposed a variety of metrics for quantifying deviations from various statistical parities that we might hope to observe in a fair world, offering a variety of algorithms that attempt to satisfy subsets of these parities or to trade off the degree to which they are satisfied against utility. In this paper, we connect this approach to fair machine learning to the literature on ideal and non-ideal methodological approaches in political philosophy. The ideal approach requires positing the principles according to which a just world would operate. In the most straightforward application of ideal theory, one supports a proposed policy by arguing that it closes a discrepancy between the real and ideal worlds. However, by failing to account for the mechanisms by which our non-ideal world arose, the responsibilities of various decision-makers, and the impacts of their actions, naive applications of ideal thinking can lead to misguided policies. In this paper, we demonstrate a connection between the recent literature on fair machine learning and the ideal approach in political philosophy, and show that some recently uncovered shortcomings in proposed algorithms reflect broader troubles faced by the ideal approach. We work this analysis through for different formulations of fairness and conclude with a critical discussion of real-world impacts and directions for new research.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Dwork, C., Hardt, M., Pitassi, T., Reingold, O., & Zemel, R. (2012) · Proceedings of the 3rd Innovations in Theoretical Computer Science Conference · doi:10.1145/2090236.2090255 · Cited by 3,501
Barocas, S., & Selbst, A. D. (2014) · doi:10.2139/ssrn.2477899 · Cited by 3,048 · cited 2×
“Machine Learning (ML) models play increasingly prominent roles in the allocation of social benefits and burdens in numerous sensitive domains, including hiring, social services, and criminal justice [4, 9, 3, 18].”
BackgroundEquality of Opportunity in Supervised Learning
Hardt, M., Price, E., & Srebro, N. (2016) · arXiv · doi:10.48550/arxiv.1610.02413 · Cited by 2,536 · cited 4×
“In the language of statistics, for example, one can require that while there may be some correlation between Ŷ and A, the dependency must be screened off by the target variable, Y [23].”
BackgroundInfluentialFair prediction with disparate impact: a study of bias in recidivism prediction instruments
Chouldechova, A. (2017) · Big Data · doi:10.1089/big.2016.0047 · Cited by 2,159 · cited 2×
“However, progress has been hindered by disagreements over the appropriate conceptualization and formalization of fairness [7, 30, 21, 5].”
BackgroundCertifying and Removing Disparate Impact
Feldman, M., Friedler, S. A., Moeller, J., Scheidegger, C., & Venkatasubramanian, S. (2015) · Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2783258.2783311 · Cited by 1,827
Fairness and Abstraction in Sociotechnical Systems
Selbst, A. D., Boyd, D., Friedler, S. A., Venkatasubramanian, S., & Vertesi, J. (2019) · Proceedings of the Conference on Fairness, Accountability, and Transparency · doi:10.1145/3287560.3287598 · Cited by 1,631
Data preprocessing techniques for classification without discrimination
Kamiran, F., & Calders, T. (2012) · Knowledge and Information Systems · doi:10.1007/s10115-011-0463-8 · Cited by 1,305 · cited 1×
“, Kamiran and Calders [28]); (ii) in the learning stage to create “fair learning” (e.”
BackgroundFairness in Criminal Justice Risk Assessments: The State of the Art
Berk, R., Heidari, H., Jabbari, S., Kearns, M., & Roth, A. (2021) · Sociological Methods & Research · doi:10.1177/0049124118782533 · Cited by 988
Inherent trade-offs in the fair determination of risk scores
Kleinberg, J., Mullainathan, S., & Raghavan, M. (2017) · Schloss Dagstuhl – Leibniz-Zentrum für Informatik · doi:10.4230/lipics.itcs.2017.43 · Cited by 943 · cited 2×
“However, progress has been hindered by disagreements over the appropriate conceptualization and formalization of fairness [7, 30, 21, 5].”
BackgroundInherent Trade-Offs in the Fair Determination of Risk Scores
Kleinberg, J., Mullainathan, S., & Raghavan, M. (2016) · arXiv · doi:10.48550/arxiv.1609.05807 · Cited by 941
Fairness in Machine Learning: Lessons from Political Philosophy
Binns, R. (2017) · arXiv · doi:10.48550/arxiv.1712.03586 · Cited by 676
Zafar, M. B., Valera, I., Gomez Rodriguez, M., & Gummadi, K. P. (2017) · Proceedings of the 26th International Conference on World Wide Web · doi:10.1145/3038912.3052660 · Cited by 632 · cited 3×
“procedures, objective functions, or learning algorithms [23, 60, 38, 29, 10, 22, 8].”
BackgroundInfluentialThe Measure and Mismeasure of Fairness
Corbett-Davies, S., Gaebler, J. D., Nilforoshan, H., Shroff, R., & Goel, S. (2018) · arXiv · doi:10.48550/arxiv.1808.00023 · Cited by 444
Avoiding Discrimination through Causal Reasoning
Kilbertus, N., Rojas-Carulla, M., Parascandolo, G., Hardt, M., Janzing, D., & Schölkopf, B. (2017) · arXiv · doi:10.48550/arxiv.1706.02744 · Cited by 358
A meta-analysis of empirical studies of weight-based bias in the workplace
Rudolph, C. W., Wells, C. L., Weller, M. D., & Baltes, B. B. (2009) · Journal of Vocational Behavior · doi:10.1016/j.jvb.2008.09.008 · Cited by 228 · cited 1×
“However, consider a casewhere the appraisal of an employee’s performance is influenced by factors such as their weight or height, despite the irrelevance (in a causal sense) of such characteristics to that job [26, 50].”
BackgroundBrown, A., Chouldechova, A., Putnam-Hornstein, E., Tobin, A., & Vaithianathan, R. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300271 · Cited by 207
Glymour, B., & Herington, J. (2019) · Proceedings of the Conference on Fairness, Accountability, and Transparency · doi:10.1145/3287560.3287573 · Cited by 50 · cited 1×
“rocedures, objective functions, or learning algorithms [23, 60, 38, 29, 10, 22, 8]. However, progress has been hindered bydisagreementsover theappropriate conceptualizationand formalizationoffairness [7,30, 21,5]. Thepersistenceofsuchdisagreementsraisesafundamentalmethodologicalquestionabouttheappropriate approach for…”
Method
Cited by
Cheong, B. C. (2024) · Frontiers in Human Dynamics · doi:10.3389/fhumd.2024.1421273 · Cited by 445
Armoundas, A. A., Narayan, S. M., Arnett, D. K., Spector-Bagdady, K., Bennett, D. A., Celi, L. A., Friedman, P. A., Gollob, M. H., Hall, J. L., Kwitek, A. E., et al. (2024) · Circulation · doi:10.1161/cir.0000000000001201 · Cited by 347
“173,175 Although debiasing provides an opportunity to incorporate social determinants of health to better identify populations for AI/ML models, 176 some clinicians have called for a reevaluation of this practice.”
BackgroundRakova, B., Yang, J., Cramer, H., & Chowdhury, R. (2021) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3449081 · Cited by 329
Algorithmic bias: Senses, sources, solutions
Fazelpour, S., & Danks, D. (2021) · Philosophy Compass · doi:10.1111/phc3.12760 · Cited by 272
Self-citationEthics as a Service: A Pragmatic Operationalisation of AI Ethics
Morley, J., Elhalal, A., Garcia, F., Kinsey, L., Mökander, J., & Floridi, L. (2021) · Minds and Machines · doi:10.1007/s11023-021-09563-w · Cited by 266
Metadata
- Authors
- Fazelpour, S., & Lipton, Z. C.
- Venue
- Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society
- Publisher
- ACM
- Published
- 2020-02-07
- Pages
- 57-63
- ISSN
- 3065-8365 (ISSN-L)
- OpenAlex
- W3000972303
- Cited by
- 119
- References
- 17
- FWCI
- 16.43
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.