{"id":13684791,"url":"https://github.com/emergingtechpolicy/awesome-ai-fairness","last_synced_at":"2025-05-01T00:33:02.190Z","repository":{"id":90883988,"uuid":"175771126","full_name":"emergingtechpolicy/awesome-ai-fairness","owner":"emergingtechpolicy","description":"Awesome list of AI Fairness tools, research papers, tutorials and any other relevant materials. For use by data scientists, AI engineers and policymakers alike.","archived":false,"fork":false,"pushed_at":"2019-03-15T08:13:25.000Z","size":11,"stargazers_count":16,"open_issues_count":0,"forks_count":2,"subscribers_count":5,"default_branch":"master","last_synced_at":"2024-05-22T05:02:27.336Z","etag":null,"topics":["fairness-ai","fairness-ml"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/emergingtechpolicy.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2019-03-15T07:33:54.000Z","updated_at":"2022-08-01T07:31:26.000Z","dependencies_parsed_at":"2023-07-26T10:54:38.666Z","dependency_job_id":null,"html_url":"https://github.com/emergingtechpolicy/awesome-ai-fairness","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/emergingtechpolicy%2Fawesome-ai-fairness","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/emergingtechpolicy%2Fawesome-ai-fairness/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/emergingtechpolicy%2Fawesome-ai-fairness/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/emergingtechpolicy%2Fawesome-ai-fairness/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/emergingtechpolicy","download_url":"https://codeload.github.com/emergingtechpolicy/awesome-ai-fairness/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":224230599,"owners_count":17277372,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["fairness-ai","fairness-ml"],"created_at":"2024-08-02T14:00:38.802Z","updated_at":"2024-11-12T06:30:37.178Z","avatar_url":"https://github.com/emergingtechpolicy.png","language":null,"funding_links":[],"categories":["Other awesome AI lists"],"sub_categories":[],"readme":"# Awesome AI Fairness [![Awesome](https://awesome.re/badge.svg)](https://awesome.re)\n\n## Toolkits and Open-source libraries\n[IBM's AI Fairness 360](https://aif360.mybluemix.net/) (most comprehensive to date)\nMost comprehensive AI Fairness toolkit to date.\n\n### Bias Detection\n[Fairness Measures](http://www.fairness-measures.org/)\nFairness benchmarking tool for machine learning – provides several fairness metrics like difference of means, disparate impact and odds ratio, along with datasets though some are not in the public domain.\n\n[FairML](https://github.com/adebayoj/fairml)\nAuditing tool for blackbox predictive models by quantifying the relative effects of various input on the model's predictions\n\n[Fairtest](https://github.com/columbia/fairtest)\nChecks for associations between predicted labels and protected attributes. Provides a way to identify regions of the input space where an algorithm might incur unusually high errors. Also includes a catalog of many datasets.\n\n[Aequitas](https://dsapp.uchicago.edu/projects/aequitas/) (*not for commerical use*)\nFriendly for both data scientists and policymakers, with a Python library and a website to upload data for bias analysis. Several fairness maetrics (demographic, statistical parity, disparate impact etc.) and a \"fairness tree\" to help users identify the correct metric to use for their particular situation.\n\n[Themis](https://github.com/LASER-UMASS/Themis)\nAutomatically generates test suites to measure discrimination in decisions made by a predictive system\n\n### Bias Detection and Mitigation\n[Themis-ML](https://github.com/cosmicBboy/themis-ml)\nHas both fairness metrics and bias mitigation algorithms like relabeling, additive counterfactually fair estimator, and reject option classification.\n\n[Fairness Comparison](https://github.com/algofairness/fairness-comparison)\nSeveral bias detection metrics and bias mitigation methods like disparate impact remover, prejudice remover and two-Naive Bayes.\n\n## Research Papers \n\nElisa Celis, Lingxiao Huang, Vijay Keswani, Nisheeth Vishnoi, [“Classification with Fairness Constraints: A Meta-Algorithm with Provable Guarantees”](https://arxiv.org/abs/1806.06055), 2018\n\nBrian Hu Zhang, Blake Lemoine, and Margaret Mitchell, [“Mitigating Unwanted Biases with Adversarial Learning”](http://www.aies-conference.com/wp-content/papers/main/AIES_2018_paper_162.pdf), AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society, 2018.\n\nTill Speicher, Hoda Heidari, Nina Grgic-Hlaca, Krishna P. Gummadi, Adish Singla, Adrian Weller, and Muhammad Bilal Zafar, [“A Unified Approach to Quantifying Algorithmic Unfairness: Measuring Individual \u0026 Group Unfairness via Inequality Indices”](https://doi.org/10.1145/3219819.3220046), ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2018.\n\nFlavio P. Calmon, Dennis Wei, Bhanukiran Vinzamuri, Karthikeyan Natesan Ramamurthy, and Kush R. Varshney, [“Optimized Pre-Processing for Discrimination Prevention”](http://papers.nips.cc/paper/6988-optimized-pre-processing-for-discrimination-prevention), Conference on Neural Information Processing Systems, 2017.\n\nGeoff Pleiss, Manish Raghavan, Felix Wu, Jon Kleinberg, and Kilian Q. Weinberger, [“On Fairness and Calibration”](https://papers.nips.cc/paper/7151-on-fairness-and-calibration), Conference on Neural Information Processing Systems, 2017.\n\nMoritz Hardt, Eric Price, and Nathan Srebro, [“Equality of Opportunity in Supervised Learning”](https://papers.nips.cc/paper/6374-equality-of-opportunity-in-supervised-learning), Conference on Neural Information Processing Systems, 2016.\n\nMichael Feldman, Sorelle A. Friedler, John Moeller, Carlos Scheidegger, and Suresh Venkatasubramanian, [“Certifying and Removing Disparate Impact”](https://doi.org/10.1145/2783258.2783311), ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2015.\n\nRichard Zemel, Yu (Ledell) Wu, Kevin Swersky, Toniann Pitassi, and Cynthia Dwork, [“Learning Fair Representations”](http://proceedings.mlr.press/v28/zemel13.html), International Conference on Machine Learning, 2013.\n\nFaisal Kamiran and Toon Calders, [“Data Preprocessing Techniques for Classification without Discrimination”](http://doi.org/10.1007/s10115-011-0463-8), Knowledge and Information Systems, 2012.\n\nFaisal Kamiran, Asim Karim, and Xiangliang Zhang, [“Decision Theory for Discrimination-Aware Classification”](https://doi.org/10.1109/ICDM.2012.45), IEEE International Conference on Data Mining, 2012.\n\nToshihiro Kamishima, Shotaro Akaho, Hideki Asoh, and Jun Sakuma, [“Fairness-Aware Classifier with Prejudice Remover Regularizer”](https://rd.springer.com/chapter/10.1007/978-3-642-33486-3_3), Joint European Conference on Machine Learning and Knowledge Discovery in Databases, 2012.\n\n\n\n\n\n\n\n## License\n\n[![CC0](http://mirrors.creativecommons.org/presskit/buttons/88x31/svg/cc-zero.svg)](https://creativecommons.org/publicdomain/zero/1.0/)\n\nTo the extent possible under law, the Emerging Technologies Policy Forum has waived all copyright and related or neighboring rights to this work.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Femergingtechpolicy%2Fawesome-ai-fairness","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Femergingtechpolicy%2Fawesome-ai-fairness","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Femergingtechpolicy%2Fawesome-ai-fairness/lists"}