LiFT: A Scalable Framework for Measuring Fairness in ML Applications
Open accessThe DOI matches its Crossref record; 20 of the 20 references it cites were found in a registry or an index.
Abstract
Many internet applications are powered by machine learned models, which are usually trained on labeled datasets obtained through user feedback signals or human judgments. Since societal biases may be present in the generation of such datasets, it is possible for the trained models to be biased, thereby resulting in potential discrimination and harms for disadvantaged groups. Motivated by the need to understand and address algorithmic bias in web-scale ML systems and the limitations of existing fairness toolkits, we present the LinkedIn Fairness Toolkit (LiFT), a framework for scalable computation of fairness metrics as part of large ML systems. We highlight the key requirements in deployed settings, and present the design of our fairness measurement system. We discuss the challenges encountered in incorporating fairness tools in practice and the lessons learned during deployment at LinkedIn. Finally, we provide open problems based on practical experience.
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
Apache Spark: A unified engine for big data processing
Zaharia, M., Xin, R. S., Wendell, P., Das, T., Armbrust, M., Dave, A., Meng, X., Rosen, J., Venkataraman, S., Franklin, M. J., et al. (2016) · Communications of the ACM · doi:10.1145/2934664 · Cited by 2,757
Model Cards for Model Reporting
Mitchell, M., Wu, S., Zaldivar, A., Barnes, P., Vasserman, L., Hutchinson, B., Spitzer, E., Raji, I. D., & Gebru, T. (2019) · Proceedings of the Conference on Fairness, Accountability, and Transparency · doi:10.1145/3287560.3287596 · Cited by 2,681 · cited 1×
“multaneously achieved. We thus need to consider ML fairness in the context of specific definitions and requirements, and make note of any caveats or assumptions upfront, using model cards for example [23]. Statistical notions of fairness are necessary to enable bias measurement over large noisy datasets, providing mea…”
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 1×
“, i.e., |P(Yˆ = 1|G = д1)− P(Yˆ = 1|G = д2)|. We also compute additional metrics such as Equalized Odds, which captures the differences in True and False Positive Rates for different protected groups [18]: δEO(y,д1,д2)= |P(Yˆ = 1|Y = y,G = д1)−P(Yˆ = 1|Y = y,G = д2)|. (2) Aggregate Fairness Metrics: These are inequali…”
Fair 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 1×
“In non-trivial cases of unequal prevalence rates, differences in model performance across subgroups can be expected due to the impossibility results [9].”
BackgroundBellamy, R. K. E., Dey, K., Hind, M., Hoffman, S. C., Houde, S., Kannan, K., Lohia, P., Martino, J., Mehta, S., Mojsilovic, A., et al. (2018) · arXiv · doi:10.48550/arxiv.1810.01943 · Cited by 1,581
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 2×
“…we present the architecture of a fairness solution that integrates with almost all stages of the ML lifecycle (Figure 1): Before training: This step deals with measuring metrics for rep-resentativeness and label distribution across different subgroups, as well as mitigation techniques such as [20].”
MethodA Reductions Approach to Fair Classification
Agarwal, A., Beygelzimer, A., Dudík, M., Langford, J., & Wallach, H. (2018) · arXiv · doi:10.48550/arxiv.1803.02453 · Cited by 1,288
AI Fairness 360: An extensible toolkit for detecting and mitigating algorithmic bias
Bellamy, R. K. E., Dey, K., Hind, M., Hoffman, S. C., Houde, S., Kannan, K., Lohia, P., Martino, J., Mehta, S., Mojsilović, A., et al. (2019) · IBM Journal of Research and Development · doi:10.1147/jrd.2019.2942287 · Cited by 884
Improving Fairness in Machine Learning Systems: What Do Industry Practitioners Need?
Holstein, K., Wortman Vaughan, J., Daumé, H., Dudik, M., & Wallach, H. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300830 · Cited by 777
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 · cited 1×
“Furthermore, black-box mitigation techniques like [3] or in-processing methods like [21] can be integrated as part of this module to obtain models that are optimal with respect to both performance and bias.”
MethodA comparative study of fairness-enhancing interventions in machine learning
Friedler, S. A., Scheidegger, C., Venkatasubramanian, S., Choudhary, S., Hamilton, E. P., & Roth, D. (2019) · Proceedings of the Conference on Fairness, Accountability, and Transparency · doi:10.1145/3287560.3287589 · Cited by 601
Aequitas: A Bias and Fairness Audit Toolkit
Saleiro, P., Kuester, B., Hinkson, L., London, J., Stevens, A., Anisfeld, A., Rodolfa, K. T., & Ghani, R. (2018) · arXiv · doi:10.48550/arxiv.1811.05577 · Cited by 496
Fairness testing: testing software for discrimination
Galhotra, S., Brun, Y., & Meliou, A. (2017) · Proceedings of the 2017 11th Joint Meeting on Foundations of Software Engineering · doi:10.1145/3106237.3106277 · Cited by 405 · cited 2×
“…be measured, provide a suite of bias mitigation techniques, or enable the comparison of fairness metrics across various algorithms [2, 3, 5, 7, 12, 13, 26, 27, 31, 33], our experience at LinkedIn suggests that none of them addresses the need for tackling these problems at scale or integrating…”
BackgroundDisparate Interactions: An Algorithm-in-the-Loop Analysis of Fairness in Risk Assessments
Green, B., & Chen, Y. (2019) · Proceedings of the Conference on Fairness, Accountability, and Transparency · doi:10.1145/3287560.3287563 · Cited by 275 · cited 1×
“ches for measuring fairness for the product/service as a whole. Another potential direction is to explore notions and definitions of fairness for ‘human-in-the-loop’ / ‘algorithm-in-the-loop’ systems [16]. Whether collected from users or inferred, there is the possibility of errors in the values of protected attribute…”
BackgroundSpeicher, T., Heidari, H., Grgic-Hlaca, N., Gummadi, K. P., Singla, A., Weller, A., & Zafar, M. B. (2018) · Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining · doi:10.1145/3219819.3220046 · Cited by 207
Srivastava, M., Heidari, H., & Krause, A. (2019) · Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining · doi:10.1145/3292500.3330664 · Cited by 179
FairTest: Discovering Unwarranted Associations in Data-Driven Applications
Tramèr, F., Atlidakis, V., Geambasu, R., Hsu, D., Hubaux, J.-P., Humbert, M., Juels, A., & Lin, H. (2015) · arXiv · doi:10.48550/arxiv.1510.02377 · Cited by 171
FairTest: Discovering Unwarranted Associations in Data-Driven Applications
Tramer, F., Atlidakis, V., Geambasu, R., Hsu, D., Hubaux, J.-P., Humbert, M., Juels, A., & Lin, H. (2017) · 2017 IEEE European Symposium on Security and Privacy (EuroS&P) · doi:10.1109/eurosp.2017.29 · Cited by 171 · cited 3×
“toolkits that offer a comprehensive set of fairness metrics that can be measured, provide a suite of bias mitigation techniques, or enable the comparison of fairness metrics across various algorithms [2, 3, 5, 7, 12, 13, 26, 27, 31, 33], our experience at LinkedIn suggests that none of them addresses the need for tack…”
BackgroundMethodPutting Fairness Principles into Practice: Challenges, Metrics, and Improvements
Beutel, A., Chen, J., Doshi, T., Qian, H., Woodruff, A., Luu, C., Kreitmann, P., Bischof, J., & Chi, E. H. (2019) · Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3306618.3314234 · Cited by 111
Grgić-Hlača, N., Redmiles, E. M., Gummadi, K. P., & Weller, A. (2018) · arXiv · doi:10.48550/arxiv.1802.09548 · Cited by 75
Cited by
Fairness and Bias in Algorithmic Hiring: A Multidisciplinary Survey
Fabris, A., Baranowska, N., Dennis, M. J., Graus, D., Hacker, P., Saldivar, J., Zuiderveen Borgesius, F., & Biega, A. J. (2025) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3696457 · Cited by 117
Andrus, M., Spitzer, E., Brown, J., & Xiang, A. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445888 · Cited by 111
Fairness-Aware Machine Learning Engineering: How Far Are We?
Ferrara, C., Sellitto, G., Ferrucci, F., Palomba, F., & De Lucia, A. (2024) · Empirical Software Engineering · doi:10.1007/s10664-023-10402-y · Cited by 60
“assumptions that people make during development (Vasudevan and Kenthapadi 2020).”
Establishing and evaluating trustworthy AI: overview and research challenges
Kowald, D., Scher, S., Pammer-Schindler, V., Müllner, P., Waxnegger, K., Demelius, L., Fessl, A., Toller, M., Mendoza Estrada, I. G., Šimić, I., et al. (2024) · Frontiers in Big Data · doi:10.3389/fdata.2024.1467222 · Cited by 59
Behavioral Use Licensing for Responsible AI
Contractor, D., McDuff, D., Haines, J. K., Lee, J., Hines, C., Hecht, B., Vincent, N., & Li, H. (2022) · 2022 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3531146.3533143 · Cited by 54
Metadata
- Authors
- Vasudevan, S., & Kenthapadi, K.
- Venue
- Proceedings of the 29th ACM International Conference on Information & Knowledge Management
- Publisher
- ACM
- Published
- 2020-10-19
- Pages
- 2773-2780
- ISSN
- 2155-0751 (ISSN-L)
- OpenAlex
- W3048991518
- Cited by
- 55
- References
- 20
- FWCI
- 8.35
- 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.