[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123614-en":3,"doc-seo-123614-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},123614,687197100911,"Himbo","https://ap-avatar.wpscdn.com/avatar/a000239b6f1da00475?x-image-process=image/resize,m_fixed,w_180,h_180&k=1785132997149421697",8,"Research & Report","What-is and How-to for Fairness in Machine Learning - A Survey, Reflection, and Perspective","The document reviews and reflects on algorithmic fairness notions proposed in machine learning, drawing connections to arguments from moral and political philosophy, with special focus on theories of justice. It surveys dynamic fairness inquiries and examines long-term effects induced by current prediction and decision. A flowchart is provided to capture implicit assumptions and expected outcomes across the data generating process, predicted outcome, and induced impact. It emphasizes matching the fairness mission with the appropriate fairness spectrum to achieve intended goals.","arXiv :2206 .04 10 1v2 [ cs .LG] 2 Jun 2023  \nWhat-is and How-to for Fairness in Machine Learning: A Survey, Reflection, and Perspective  \nZEYU TANG, Carnegie Mellon University, United States  \nJIJI ZHANG, The Chinese University of Hong Kong, Hong Kong KUN ZHANG, Carnegie Mellon University, United States  \nWe review and reflect on fairness notions proposed in machine learning literature, and make an attempt to draw connections to arguments in moral and political philosophy, especially theories of justice. We survey dynamic fairness inquiries, and further consider the long-term impact induced by current prediction and decision. We present a flowchart that encompasses implicit assumptions and expected outcomes of different fairness inquiries on the data generating process, the predicted outcome, and the induced impact, respectively. We demonstrate the importance of matching the mission (what kind of fairness to enforce) and the means (which appropriate fairness spectrum to analyze) to fulfill the intended purpose.  \nCCS Concepts: • Computing methodologies → Artificial intelligence; Machine learning.  \nAdditional Key Words and Phrases: Algorithmic fairness, causality, bias mitigation, dynamic process, fair machine learning  \nACM Reference Format:  \nZeyu Tang, Jiji Zhang, and Kun Zhang. 2023. What-is and How-to for Fairness in Machine Learning: A Survey,  \nReflection, and Perspective. ACM Comput. Surv.00, JA, Article00(May2023),38pages. [https://doi.org/10.1145/3597199](https://doi.org/10.1145/3597199)  \n1 INTRODUCTION  \nWith the widespread utilization of machine learning models in our daily life, researchers have been thinking about the potential social consequences of the prediction/decision made by algorithms. To date, there is ample evidence that machine learning models have resulted in discrimination against certain groups of individuals under many circumstances, for instance, the discrimination in ad delivery when searching for names that can be predictive of the race of an individual [174]; the gender discrimination in job-related ads push [48]; stereotypes associated with gender in word embeddings [22]; the bias against certain ethnic groups in the assessment of recidivism risk [7, 19]; the violation of anti-discrimination law (e.g., Title VII of the 1964 Civil Rights Act) in data mining [13] .  \nKun Zhang also with Mohamed bin Zayed University of Artificial Intelligence, United Arab Emirates.  \nThe work was supported in part by the NSF-Convergence Accelerator Track-D award No. 2134901, by the National Institutes of Health (NIH) under Contract No. R01HL159805, by grants from Apple Inc., KDDI Research, Quris AI, and IBT, and by generous gifts from Amazon, Microsoft Research, and Salesforce. J.Z.’s research was supported in part by the RGC of Hong Kong (Grant No. GRF 13602720) .  \nAuthors’ addresses: Z. Tang and K. Zhang, Department of Philosophy, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA 15213 USA; emails: {zeyutang, [kunz1}@cmu.edu](kunz1}@cmu.edu); J. Zhang, Department of Philosophy, The Chinese University of Hong Kong, Shatin, New Territories, Hong Kong; [email: jijizhang@cuhk.edu.hk](email: jijizhang@cuhk.edu.hk).  \nPermission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the owner/author(s) .  \n© 2023 Copyright held by the owner/author(s) .  \n0360-0300/2023/05-ART00  \n[https://doi.org/10.1145/3597199](https://doi.org/10.1145/3597199)  \nACM Comput. Surv., Vol. 00, No. JA, Article 00 . Publication date: May 2023 . Preprint.  \nIn the effort of enforcing fairness in machine learning, various notions as well as techniques to regulate discrimination under different scenarios have been proposed in the ","cbCaivjG4BNdo9nk","https://ap.wps.com/l/cbCaivjG4BNdo9nk","pdf",839593,1,38,"English","en",105,"# Introduction\n## Motivation: Social consequences of ML predictions and decisions\n## Categorizing fairness notions (associative vs. causal)\n## Fairness scope (group-level vs. individual-level)\n## Techniques for bias mitigation (pre-, in-, post-processing)\n## Fairness in dynamic settings\n## Prior surveys and missing philosophical clarity","[{\"question\":\"What main goal does the survey pursue regarding fairness in machine learning?\",\"answer\":\"It reviews and reflects on fairness notions in ML literature and builds connections to justice-related arguments from moral and political philosophy.\"},{\"question\":\"How does the document organize fairness notions?\",\"answer\":\"It distinguishes associative vs. causal fairness, group-level vs. individual-level fairness, and pre-, in-, and post-processing approaches, also covering dynamic fairness over time.\"},{\"question\":\"What is the key methodological message about enforcing fairness?\",\"answer\":\"Fairness should be aligned so the mission (which kind of fairness to enforce) matches the means (which fairness spectrum to analyze) to fulfill the intended purpose.\"}]","What-is and How-to for Fairness in Machine Learning - A Survey, Reflection, and Perspective | PDF",1785817636,96,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"what-is-and-how-to-for-fairness-in-machine-learning-a-survey-reflection-and-perspective","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/what-is-and-how-to-for-fairness-in-machine-learning-a-survey-reflection-and-perspective/123614/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What main goal does the survey pursue regarding fairness in machine learning?","Question",{"text":75,"@type":76},"It reviews and reflects on fairness notions in ML literature and builds connections to justice-related arguments from moral and political philosophy.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the document organize fairness notions?",{"text":80,"@type":76},"It distinguishes associative vs. causal fairness, group-level vs. individual-level fairness, and pre-, in-, and post-processing approaches, also covering dynamic fairness over time.",{"name":82,"@type":73,"acceptedAnswer":83},"What is the key methodological message about enforcing fairness?",{"text":84,"@type":76},"Fairness should be aligned so the mission (which kind of fairness to enforce) matches the means (which fairness spectrum to analyze) to fulfill the intended purpose.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]