Towards Fairness in Practice: A Practitioner-Oriented Rubric for Evaluating Fair ML Toolkits
The DOI matches its Crossref record; 25 of the 25 references it cites were found in a registry or an index.
Abstract
In order to support fairness-forward thinking by machine learning (ML) practitioners, fairness researchers have created toolkits that aim to transform state-of-the-art research contributions into easily-accessible APIs. Despite these efforts, recent research indicates a disconnect between the needs of practitioners and the tools offered by fairness research. By engaging 20 ML practitioners in a simulated scenario in which they utilize fairness toolkits to make critical decisions, this work aims to utilize practitioner feedback to inform recommendations for the design and creation of fair ML toolkits. Through the use of survey and interview data, our results indicate that though fair ML toolkits are incredibly impactful on users’ decision-making, there is much to be desired in the design and demonstration of fairness results. To support the future development and evaluation of toolkits, this work offers a rubric that can be used to identify critical components of Fair ML toolkits.
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
Crenshaw, K. (2018) · Living with Contradictions · doi:10.4324/9780429499142-5 · Cited by 7,232
The global landscape of AI ethics guidelines
Jobin, A., Ienca, M., & Vayena, E. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0088-2 · Cited by 6,220 · cited 2×
“These guidelines focus on themes like fairness, transparency, accountability, and so on [28].”
BackgroundA Survey on Bias and Fairness in Machine Learning
Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., & Galstyan, A. (2019) · arXiv · doi:10.48550/arxiv.1908.09635 · Cited by 5,812
A Survey on Bias and Fairness in Machine Learning
Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., & Galstyan, A. (2022) · ACM Computing Surveys · doi:10.1145/3457607 · Cited by 5,812
Algorithms of Oppression: How Search Engines Reinforce Racism
Noble, S. U. (2020) · doi:10.2307/j.ctt1pwt9w5 · Cited by 2,709
Bellamy, 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 · cited 5×
“ment (Google Colaboratory) and their choice of visual aids which are infuential in the fairness consideration process [9].”
BackgroundInfluentialData 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×
“For Random Forest, the model was optimized to satisfy Demographic Parity, which states the proportion of people in each demographic group classifed in the positive class should be equivalent [30].”
MethodFairness definitions explained
Verma, S., & Rubin, J. (2018) · Proceedings of the International Workshop on Software Fairness · doi:10.1145/3194770.3194776 · Cited by 1,124
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 · cited 10×
“As previous work [27, 34, 35, 37, 50] suggests, practitioner feedback is of the utmost importance for successful and meaningful fairness impact.”
BackgroundResultInfluential
Cited by
Sociotechnical Harms of Algorithmic Systems: Scoping a Taxonomy for Harm Reduction
Shelby, R., Rismani, S., Henne, K., Moon, A., Rostamzadeh, N., Nicholas, P., Yilla-Akbari, N., Gallegos, J., Smart, A., Garcia, E., et al. (2023) · Proceedings of the 2023 AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3600211.3604673 · Cited by 279
“As such, it presents navigational challenges for practitioners seeking to comprehensively evaluate a system for potential harms [178, 179, 182], particularly for large generative models that perform different tasks across many use cases.”
BackgroundAssessing the Fairness of AI Systems: AI Practitioners' Processes, Challenges, and Needs for Support
Madaio, M., Egede, L., Subramonyam, H., Wortman Vaughan, J., & Wallach, H. (2022) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3512899 · Cited by 156
Seeing Like a Toolkit: How Toolkits Envision the Work of AI Ethics
Wong, R. Y., Madaio, M. A., & Merrill, N. (2023) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3579621 · Cited by 135
Deng, W. H., Guo, B., Devrio, A., Shen, H., Eslami, M., & Holstein, K. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581026 · Cited by 103
Exploring How Machine Learning Practitioners (Try To) Use Fairness Toolkits
Deng, W. H., Nagireddy, M., Lee, M. S. A., Singh, J., Wu, Z. S., Holstein, K., & Zhu, H. (2022) · 2022 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3531146.3533113 · Cited by 99
“Support for such “just-in-time” learning could help alleviate challenges identified in prior studies on fairness toolkits, in which practitioners struggled to pinpoint the resources they needed the most [63, 89].”
BackgroundInfluentialWidder, D. G., Zhen, D., Dabbish, L., & Herbsleb, J. (2023) · 2023 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3593013.3594012 · Cited by 94
“Ethics interventions such as toolkits [39, 57], checklists [42], principles [33], and education [18] are often designed to help practitioners identify issues, and flag them to others using artifacts such as model cards [46] or datasheets [20].”
BackgroundMim, N. J., Nandi, D., Khan, S. S., Dey, A., & Ahmed, S. I. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3641951 · Cited by 42
“…biases should be addressed at the design level, either by accounting for the statistical sampling in the data and sentiment analysis over the associated texts or by compensating for any negative portrayal by allowing human-in-the-loop interventions while producing the output [94, 109, 149].”
BackgroundWatkins, E. A., McKenna, M., & Chen, J. (2022) · arXiv · doi:10.48550/arxiv.2202.09519 · Cited by 35
Watkins, E. A., & Chen, J. (2024) · The 2024 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3630106.3658938 · Cited by 25
A step toward building a unified framework for managing AI bias
Rana, S. A., Azizul, Z. H., & Awan, A. A. (2023) · PeerJ Computer Science · doi:10.7717/peerj-cs.1630 · Cited by 23
Kallina, E., & Singh, J. (2025) · Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706599.3719726 · Cited by 6
Metadata
- Authors
- Richardson, B., Garcia-Gathright, J., Way, S. F., Thom, J., & Cramer, H.
- Venue
- Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems
- Publisher
- ACM
- Published
- 2021-05-06
- Pages
- 1-13
- OpenAlex
- W3160967115
- Cited by
- 56
- References
- 25
- FWCI
- 9.79
- Type
- conference paper
- Language
- en
- Open access
- closed
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.