{"id":13472817,"url":"https://github.com/fairlearn/fairlearn","last_synced_at":"2025-05-12T13:23:13.448Z","repository":{"id":37979492,"uuid":"133444044","full_name":"fairlearn/fairlearn","owner":"fairlearn","description":"A Python package to assess and improve fairness of machine learning models.","archived":false,"fork":false,"pushed_at":"2025-05-05T13:40:48.000Z","size":80009,"stargazers_count":2058,"open_issues_count":134,"forks_count":452,"subscribers_count":37,"default_branch":"main","last_synced_at":"2025-05-05T14:49:21.283Z","etag":null,"topics":["ai","ai-systems","artificial-intelligence","fairness","fairness-ai","fairness-assessment","fairness-ml","group-fairness","harms","machine-learning","responsible-ai","unfairness-mitigation"],"latest_commit_sha":null,"homepage":"https://fairlearn.org","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/fairlearn.png","metadata":{"files":{"readme":"README.rst","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2018-05-15T01:51:35.000Z","updated_at":"2025-05-05T13:40:53.000Z","dependencies_parsed_at":"2024-01-23T14:02:47.752Z","dependency_job_id":"d5af0456-d1c1-4107-9012-13eb347c1492","html_url":"https://github.com/fairlearn/fairlearn","commit_stats":{"total_commits":853,"total_committers":90,"mean_commits":9.477777777777778,"dds":0.6576787807737398,"last_synced_commit":"3f9f7d136f15d9b40198cc098f2b96dcf6b0750e"},"previous_names":[],"tags_count":21,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fairlearn%2Ffairlearn","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fairlearn%2Ffairlearn/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fairlearn%2Ffairlearn/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fairlearn%2Ffairlearn/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/fairlearn","download_url":"https://codeload.github.com/fairlearn/fairlearn/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253745373,"owners_count":21957357,"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":["ai","ai-systems","artificial-intelligence","fairness","fairness-ai","fairness-assessment","fairness-ml","group-fairness","harms","machine-learning","responsible-ai","unfairness-mitigation"],"created_at":"2024-07-31T16:00:58.247Z","updated_at":"2025-05-12T13:23:13.424Z","avatar_url":"https://github.com/fairlearn.png","language":"Python","readme":"|MIT license| |PyPI| |Discord| |StackOverflow|\n\nFairlearn\n=========\n\nFairlearn is a Python package that empowers developers of artificial\nintelligence (AI) systems to assess their system's fairness and mitigate\nany observed unfairness issues. Fairlearn contains mitigation algorithms\nas well as metrics for model assessment. Besides the source code, this\nrepository also contains Jupyter notebooks with examples of Fairlearn\nusage.\n\nWebsite: https://fairlearn.org/\n\n-  `What we mean by *fairness* \u003c#what-we-mean-by-fairness\u003e`__\n-  `Overview of Fairlearn \u003c#overview-of-fairlearn\u003e`__\n-  `Getting started with fairlearn \u003c#getting-started-with-fairlearn\u003e`__\n-  `Maintainers \u003c#maintainers\u003e`__\n-  `Code of conduct \u003c#code-of-conduct\u003e`__\n-  `Issues \u003c#issues\u003e`__\n\nWhat we mean by *fairness*\n--------------------------\n\nAn AI system can behave unfairly for a variety of reasons. In Fairlearn,\nwe define whether an AI system is behaving unfairly in terms of its\nimpact on people – i.e., in terms of harms. We focus on two kinds of\nharms:\n\n-  *Allocation harms.* These harms can occur when AI systems extend or\n   withhold opportunities, resources, or information. Some of the key\n   applications are in hiring, school admissions, and lending.\n\n-  *Quality-of-service harms.* Quality of service refers to whether a\n   system works as well for one person as it does for another, even if\n   no opportunities, resources, or information are extended or withheld.\n\nWe follow the approach known as **group fairness**, which asks: *Which\ngroups of individuals are at risk for experiencing harms?* The relevant\ngroups need to be specified by the data scientist and are application\nspecific.\n\nGroup fairness is formalized by a set of constraints, which require that\nsome aspect (or aspects) of the AI system's behavior be comparable\nacross the groups. The Fairlearn package enables assessment and\nmitigation of unfairness under several common definitions. To learn more\nabout our definitions of fairness, please visit our\n`user guide on Fairness of AI Systems \u003chttps://fairlearn.org/main/user_guide/fairness_in_machine_learning.html#fairness-of-ai-systems\u003e`__.\n\n    *Note*: Fairness is fundamentally a sociotechnical challenge. Many\n    aspects of fairness, such as justice and due process, are not\n    captured by quantitative fairness metrics. Furthermore, there are\n    many quantitative fairness metrics which cannot all be satisfied\n    simultaneously. Our goal is to enable humans to assess different\n    mitigation strategies and then make trade-offs appropriate to their\n    scenario.\n\nOverview of Fairlearn\n---------------------\n\nThe Fairlearn Python package has two components:\n\n-  *Metrics* for assessing which groups are negatively impacted by a\n   model, and for comparing multiple models in terms of various fairness\n   and accuracy metrics.\n\n-  *Algorithms* for mitigating unfairness in a variety of AI tasks and\n   along a variety of fairness definitions.\n\nFairlearn metrics\n~~~~~~~~~~~~~~~~\n\nCheck out our in-depth `guide on the Fairlearn metrics \u003chttps://fairlearn.org/main/user_guide/assessment\u003e`__.\n\nFairlearn algorithms\n~~~~~~~~~~~~~~~~~~~\n\nFor an overview of our algorithms please refer to our\n`website \u003chttps://fairlearn.org/main/user_guide/mitigation/index.html\u003e`__.\n\nGetting Started with Fairlearn\n-----------------------------\n\nFirst steps\n~~~~~~~~~~~\n\n- Install via pip: ``pip install fairlearn``\n\n- Visit the `Quickstart guide \u003chttps://fairlearn.org/main/quickstart.html\u003e`__.\n\n- **Learning Resources**:\n\n  - Read the comprehensive `user guide \u003chttps://fairlearn.org/main/user_guide/index.html\u003e`__.\n\n  - Look through the `example notebooks \u003chttps://fairlearn.org/main/auto_examples/index.html\u003e`__.\n\n\nFor Users \u0026 Practitioners\n~~~~~~~~~~~~~~~~~~~~~~~~\n\n- Browse the `example gallery \u003chttps://fairlearn.org/main/auto_examples/index.html\u003e`__. \nPlease note that notebooks downloaded from `main` may not be compatible with pip-installed versions.\n\n- Check the `API reference \u003chttps://fairlearn.org/main/api_reference/index.html\u003e`__.\n\n- **Get Help**:\n\n  - Ask questions on `Stack Overflow \u003chttps://stackoverflow.com/questions/tagged/fairlearn\u003e`__ with tag ``fairlearn``.\n\n  - Join the `Discord community \u003chttps://discord.gg/R22yCfgsRn\u003e`__ for discussions.\n\nFor Contributors\n~~~~~~~~~~~~~~~\n\n- Read the `contributor guide \u003chttps://fairlearn.org/main/contributor_guide/index.html\u003e`__.\n\n- Check out the `good first issues \u003chttps://github.com/fairlearn/fairlearn/labels/good%20first%20issue\u003e`__.\n\n- Follow the `development process \u003chttps://fairlearn.org/main/contributor_guide/development_process.html\u003e`__.\n\n- Join the `Discord \u003chttps://discord.gg/R22yCfgsRn\u003e`__ for contributor discussions. Please use the ``#development`` channel.\n\n\nMaintainers\n-----------\n\nA list of current maintainers is\n`on our website \u003chttps://fairlearn.org/main/about/index.html\u003e`__.\n\nCode of conduct\n---------------\nFairlearn follows the `Fairlearn Organization's Code of Conduct \u003chttps://github.com/fairlearn/governance/blob/main/code-of-conduct.md\u003e`__.\n\nIssues\n------\n\nRegular (non-security) issues\n~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n\nIssues are meant for bugs, feature requests, and documentation\nimprovements. Please submit a report through\n`GitHub issues \u003chttps://github.com/fairlearn/fairlearn/issues\u003e`__.\nA maintainer will respond promptly as appropriate.\n\nMaintainers will try to link duplicate issues when possible.\n\nReporting security issues\n~~~~~~~~~~~~~~~~~~~~~~~~~\n\nTo report security issues please send an email to\n``fairlearn-internal@python.org``.\n\n.. |MIT license| image:: https://img.shields.io/badge/License-MIT-blue.svg\n   :target: https://github.com/fairlearn/fairlearn/blob/main/LICENSE\n.. |PyPI| image:: https://img.shields.io/pypi/v/fairlearn?color=blue\n   :target: https://pypi.org/project/fairlearn/\n.. |Discord| image:: https://img.shields.io/discord/840099830160031744\n   :target: https://discord.gg/R22yCfgsRn\n.. |StackOverflow| image:: https://img.shields.io/badge/StackOverflow-questions-blueviolet\n   :target: https://stackoverflow.com/questions/tagged/fairlearn\n","funding_links":[],"categories":["⚖️ Fairness, Bias \u0026 Ethics Testing","Python","Fairness Toolboxes","Deep Learning Framework","Explainability and Fairness","模型的可解释性","Awesome Privacy Engineering [![Awesome](https://awesome.re/badge.svg)](https://awesome.re)","Model Fairness and Privacy","A01_机器学习教程","\u003ca id=\"tools\"\u003e\u003c/a\u003e🛠️ Tools","Fairness Packages and Frameworks","Technical Resources","The List of AI Testing Tools","Bias and fairness"],"sub_categories":["Anomaly Detection \u0026 Others","Machine Learning and Algorithmic Bias","Model Fairness \u0026 Privacy","Mitigation of Representations","Open Source/Access Responsible AI Software Packages","10. Fairlearn"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffairlearn%2Ffairlearn","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffairlearn%2Ffairlearn","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffairlearn%2Ffairlearn/lists"}