The DOI matches its Crossref record; 15 of the 15 references it cites were found in a registry or an index.
Beyond Distributive Fairness in Algorithmic Decision Making: Feature Selection for Procedurally Fair Learning
Open accessAbstract
With widespread use of machine learning methods in numerous domains involving humans, several studies have raised questions about the potential for unfairness towards certain individuals or groups. A number of recent works have proposed methods to measure and eliminate unfairness from machine learning models. However, most of this work has focused on only one dimension of fair decision making: distributive fairness, i.e., the fairness of the decision outcomes. In this work, we leverage the rich literature on organizational justice and focus on another dimension of fair decision making: procedural fairness, i.e., the fairness of the decision making process. We propose measures for procedural fairness that consider the input features used in the decision process, and evaluate the moral judgments of humans regarding the use of these features. We operationalize these measures on two real world datasets using human surveys on the Amazon Mechanical Turk (AMT) platform, demonstrating that our measures capture important properties of procedurally fair decision making. We provide fast submodular mechanisms to optimize the tradeoff between procedural fairness and prediction accuracy. On our datasets, we observe empirically that procedural fairness may be achieved with little cost to outcome fairness, but that some loss of accuracy is unavoidable.
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
Conducting behavioral research on Amazon’s Mechanical Turk
Mason, W., & Suri, S. (2012) · Behavior Research Methods · doi:10.3758/s13428-011-0124-6 · Cited by 3,172 · cited 1×
“For gathering human judgments, we use the Amazon Mechanical Turk (AMT) platform where users (or workers) can volunteer to perform a wide range of online tasks for pay (Buhrmester, Kwang, and Gosling 2011; Mason and Suri 2012).”
MethodBarocas, S., & Selbst, A. D. (2014) · doi:10.2139/ssrn.2477899 · Cited by 3,048 · cited 4×
“6Examples of cases where, for outcome fairness, one is legally bound to ensure that a decision making process yields the fairest solution under certain performance constraints are discussed at length in (Barocas and Selbst 2016).”
BackgroundInfluentialEquality of Opportunity in Supervised Learning
Hardt, M., Price, E., & Srebro, N. (2016) · arXiv · doi:10.48550/arxiv.1610.02413 · Cited by 2,536 · cited 1×
“Finally, the notions of “disparate mistreatment” (Zafar et al. 2017a) and “equal opportunity” (Hardt, Price, and Srebro 2016) aim to achieve similar rates of errors in decision outcomes for different sensitive attribute groups.”
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
Kusner, M. J., Loftus, J. R., Russell, C., & Silva, R. (2017) · arXiv · doi:10.48550/arxiv.1703.06856 · Cited by 995 · cited 1×
“Feature relevance: Is the feature causally related or not to the decision outcomes (Kilbertus et al. 2017; Kusner et al. 2017)?”
BackgroundInherent 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 1×
“This measure is inspired by recent studies related to fairness in criminal risk assessment (Kleinberg, Mullainathan, and Raghavan 2017; Angwin et al. 2016; Zafar et al. 2017a).”
MethodInherent 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-Aware Classifier with Prejudice Remover Regularizer
Kamishima, T., Akaho, S., Asoh, H., & Sakuma, J. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-33486-3_3 · Cited by 694
Discrimination-aware data mining
Pedreshi, D., Ruggieri, S., & Turini, F. (2008) · Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/1401890.1401959 · Cited by 676 · cited 2×
“These concerns have spawned much recent research on detecting and avoiding unfairness in decision making (Dwork et al. 2012; Feldman et al. 2015; Kamiran and Calders 2010; Luong, Ruggieri, and Turini 2011; Pedreschi, Ruggieri, and Turini 2008; Zafar et al. 2017b; Zemel et al. 2013).”
Background
Cited by
Explainable AI: a review of machine learning interpretability methods
Linardatos, P., Papastefanopoulos, V., & Kotsiantis, S. (2020) · Entropy · doi:10.3390/e23010018 · Cited by 2,922
“[89] procedurally_fair_learning F G Agnostic tab 22 2018”
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
Algorithmic bias: review, synthesis, and future research directions
Kordzadeh, N., & Ghasemaghaei, M. (2022) · European Journal of Information Systems · doi:10.1080/0960085x.2021.1927212 · Cited by 770
“…algorithm or algorithmic decision as being fair, whereas procedural fairness conceptua-lises fairness perceptions with respect to internal processes of data-driven systems such as the rules and logics incorporated into algorithms (Binns et al., 2018; Grgić-Hlača et al., 2018; Robert et al., 2020).”
Trustworthy AI: From Principles to Practices
Li, B., Qi, P., Liu, B., Di, S., Liu, J., Pei, J., Yi, J., & Zhou, B. (2023) · ACM Computing Surveys · doi:10.1145/3555803 · Cited by 612
“At each granularity, we might be concerned with distributive fairness or fairness of the outcome, or procedural fairness or fairness of the process (we refer the reader to Reference [137] for a more detailed discussion).”
BackgroundTowards Robust Interpretability with Self-Explaining Neural Networks
Alvarez-Melis, D., & Jaakkola, T. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.07538 · Cited by 397
Fairness perceptions of algorithmic decision-making: A systematic review of the empirical literature
Starke, C., Baleis, J., Keller, B., & Marcinkowski, F. (2022) · Big Data & Society · doi:10.1177/20539517221115189 · Cited by 316
“As humans are ultimately affected by the decisions made by ADM, several authors advocate for a more human-centric approach to researching algorithmic fairness to ensure that ADM systems are legitimized (Grgić-Hlača et al., 2018a; Kieslich et al., 2022).”
BackgroundMethodResultInfluentialMehrotra, R., McInerney, J., Bouchard, H., Lalmas, M., & Diaz, F. (2018) · Proceedings of the 27th ACM International Conference on Information and Knowledge Management · doi:10.1145/3269206.3272027 · Cited by 279
Designing fair AI for managing employees in organizations: a review, critique, and design agenda
Robert, L. P., Pierce, C., Marquis, L., Kim, S., & Alahmad, R. (2020) · Human–Computer Interaction · doi:10.1080/07370024.2020.1735391 · Cited by 268
Classification with Fairness Constraints: A Meta-Algorithm with Provable Guarantees
Celis, L. E., Huang, L., Keswani, V., & Vishnoi, N. K. (2019) · Proceedings of the Conference on Fairness, Accountability, and Transparency · doi:10.1145/3287560.3287586 · Cited by 231
“[33, 32] discussed procedural fairness that investigates which input features are fair to use in the decision process and how including or excluding the features would affect outcomes.”
BackgroundGrgic-Hlaca, N., Redmiles, E. M., Gummadi, K. P., & Weller, A. (2018) · Proceedings of the 2018 World Wide Web Conference on World Wide Web - WWW '18 · doi:10.1145/3178876.3186138 · Cited by 207
Self-citationDemocratizing Algorithmic Fairness
Wong, P.-H. (2020) · Philosophy & Technology · doi:10.1007/s13347-019-00355-w · Cited by 182
Ethical machines: The human-centric use of artificial intelligence
Lepri, B., Oliver, N., & Pentland, A. (2021) · iScience · doi:10.1016/j.isci.2021.102249 · Cited by 149
The Butterfly Effect in Artificial Intelligence Systems: Implications for AI Bias and Fairness
Ferrara, E. (2023) · doi:10.2139/ssrn.4614234 · Cited by 129
Human Decision Making with Machine Assistance: An Experiment on Bailing and Jailing
Grgić-Hlača, N., Engel, C., & Gummadi, K. P. (2019) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3359280 · Cited by 113
“Several studies also explored human perceptions of the fairness of machine decisions, in the context of self-driving cars [5, 12], targeted-advertising [59], loan approval [62], and bail decisions [36–38 Another series of studies has compared human and machine decision-making.”
BackgroundSelf-citationBeyond generalization: a theory of robustness in machine learning
Freiesleben, T., & Grote, T. (2023) · Synthese · doi:10.1007/s11229-023-04334-9 · Cited by 106
“Several amelioration strategies have been proposed to enable procedurally fair ML models, relying on data augmentation (Sharma et al., 2020), architectural adjustments (Du et al., 2020), and feature selection (Dwork et al., 2012; Gajane & Pechenizkiy, 2017; Grgi´c-Hlaˇca et al., 2018).”
BackgroundMethodOne-Network Adversarial Fairness
Adel, T., Valera, I., Ghahramani, Z., & Weller, A. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33012412 · Cited by 95
“…earlier work, unfairness means discriminating against a particular group of people due to sensitive group characteristics such as gender or race (Grgic-Hlaca et al. 2018b; Hardt, Price, and Srebro 2016; Kusner et al. 2017; Louizos et al. 2016; Zafar et al. 2017c; 2017a; Zemel et al. 2013).”
BackgroundInfluentialSelf-citationGrgić-Hlača, N., Redmiles, E. M., Gummadi, K. P., & Weller, A. (2018) · arXiv · doi:10.48550/arxiv.1802.09548 · Cited by 75
Self-citationSchoeffer, J., Kuehl, N., & Machowski, Y. (2022) · 2022 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3531146.3533218 · Cited by 67
A survey on datasets for fairness‐aware machine learning
Le Quy, T., Roy, A., Iosifidis, V., Zhang, W., & Ntoutsi, E. (2022) · WIREs Data Mining and Knowledge Discovery · doi:10.1002/widm.1452 · Cited by 261
On the Legal Compatibility of Fairness Definitions
Xiang, A., & Raji, I. D. (2019) · arXiv · doi:10.48550/arxiv.1912.00761 · Cited by 34
Genovesi, S., Mönig, J. M., Schmitz, A., Poretschkin, M., Akila, M., Kahdan, M., Kleiner, R., Krieger, L., & Zimmermann, A. (2024) · AI and Ethics · doi:10.1007/s43681-023-00291-8 · Cited by 19
Metadata
- Authors
- Grgić-Hlača, N., Zafar, M. B., Gummadi, K. P., & Weller, A.
- Venue
- Proceedings of the AAAI Conference on Artificial Intelligence
- Published
- 2018-04-25
- Volume
- 32
- Issue
- 1
- ISSN
- 2159-5399 (ISSN-L)
- 2374-3468
- OpenAlex
- W2787955716
- Cited by
- 181
- References
- 15
- FWCI
- 32.59
- Type
- conference paper
- Language
- en
- Open access
- diamond
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.