[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125905-en":3,"doc-seo-125905-105":31,"detail-sidebar-cat-0-en-105":93},{"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":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},125905,2336474466712,"Maeve","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","FairPipes: Data Mutation Pipelines for Machine Learning Fairness","Machine Learning models are widely used in decision-making scenarios that directly affect citizens, making fairness toward protected attributes like age, gender, and race essential alongside performance. Building on existing fairness metrics and mitigation methods, the work investigates how deployed models react to perturbations in fairness-related data. It introduces mutation-based pipelines that emulate fairness variations by shuffling sensitive attributes, adding values, or altering their distributions. Experiments across seven models and three datasets reveal distinct sensitivity patterns and show that optimization influences fairness outcomes.","Institutional Repository-Research Portal Dépôt Institutionnel-Portail de la Recherche  \n University of easr[chportal.unamur.be](chportal.unamur.be)  \nRESEARCH OUTPUTS / RÉSULTATS DE RECHERCHE  \nFairPipes: Data Mutation Pipelines for Machine Learning Fairness  \nMolinier, Camille; Temple, Paul; Perrouin, Gilles  \nPublication date: 2024  \nDocument Version  \nPeer reviewed version  \nLink to publication  \nCitation for pulished version (HARVARD):  \nMolinier, C, Temple, P & Perrouin, G 2024, 'FairPipes: Data Mutation Pipelines for Machine Learning Fairness' .  \nGeneral rights  \nCopyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights.  \n• Users may download and print one copy of any publication from the public portal for the purpose of private study or research.  \n• You may not further distribute the material or use it for any profit-making activity or commercial gain  \n• You may freely distribute the URL identifying the publication in the public portal ?  \nTake down policy  \nIf you believe that this document breaches copyright please contact us providing details, and we will remove access to the work immediately and investigate your claim.  \nDownload date: 14. Oct. 2024  \nFairPipes: Data Mutation Pipelines for Machine Learning  \nFairness  \nCamille Molinier  \nESIR, University of Rennes Rennes, France  \ncamille.molinier@etudiant.univ[rennes.fr](rennes.fr)  \nPaul Temple  \nUniversity of Rennes, CNRS, Inria, IRISARennes, France [paul.temple@irisa.fr](paul.temple@irisa.fr)  \nGilles Perrouin  \nPReCISE/NaDI, University of Namur Namur, Belgium [gilles.perrouin@unamur.be](gilles.perrouin@unamur.be)  \nABSTRACT  \nMachine Learning (ML) models are ubiquitous in decisionmaking applications impacting citizens’ lives: credit attribution, crime recidivism, etc. In addition to seeking high performance and generalization abilities, ensuring that ML models do not discriminate against citizens regarding their age, gender, or race is essential. To this end, researchers developed various fairness assessment techniques, comprising fairness metrics and mitigation approaches, notably at the model level. However, the sensitivity of ML models to fairness data perturbations has been less explored. This paper presents mutation-based pipelines to emulate fairness variations in the data once the model is deployed. FairPipes implements mutation operators that shuffle sensitive attributes, add new values, or affect their distribution. We evaluated FairPipes on seven ML models over three datasets. Our results highlight different fairness sensitivity behaviors across models, from the most sensitive perceptrons to the insensitive support vector machines. We also consider the role of model optimization in fairness performance, being variable across models. FairPipes automates fairness testing at deployment time, informing researchers and practitioners on the fairness sensitivity evolution of their ML models.  \nCCS CONCEPTS  \n• Software and its engineering → Software testing and debugging; • Computing methodologies → Machine learning.  \nKEYWORDS  \nMachine Learning, Fairness, Mutation Testing  \nACM Reference Format:  \nCamille Molinier, Paul Temple, and Gilles Perrouin. 2024. FairPipes: Data Mutation Pipelines for Machine Learning Fairness. In 5th ACM/IEEE International Conference on Automation of Software Test (AST 2024) (AST ’24), April 15 –16, 2024, Lisbon, Portugal. ACM, New York, NY, USA, 11 pages. [https://doi.org/](https://doi.org/)[ ](https://doi.org/)[10.1145/3644032.3644465](10.1145/3644032.3644465)  \nAST’24, April 15– 16, 2024, Lisbon, Portugal  \n© 2024 Copyright held by the owner/author(s) . Publication rights licensed to ACM.  \nThis is the author’s version of the work. It is posted here for your personal use . Not for redistribution. The definiti","cbCais5BqZ4n40A4","https://ap.wps.com/l/cbCais5BqZ4n40A4","pdf",1426090,7,1,12,"English","en",105,"# Introduction\n## Fairness in ML and decision-making impact\n## Bias mitigation, fairness metrics, and limitations\n## Motivation: sensitivity to fairness perturbations\n## FairPipes overview (mutation-based fairness testing at deployment)","[{\"question\":\"What problem does FairPipes address in machine learning fairness?\",\"answer\":\"FairPipes targets the limited understanding of how ML models respond to fairness-data perturbations after deployment, rather than only improving fairness using metrics and mitigation at the model level.\"},{\"question\":\"How does FairPipes emulate fairness variations in data?\",\"answer\":\"FairPipes uses mutation operators that shuffle sensitive attributes, add new values, or modify their distribution to create fairness-related data variations.\"},{\"question\":\"What do experiments on multiple models and datasets show?\",\"answer\":\"Results highlight different fairness sensitivity behaviors across models and indicate that model optimization affects fairness performance in a way that varies by model.\"}]","FairPipes: Data Mutation Pipelines for Machine Learning Fairness | PDF",1785901942,30,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":88,"head_meta":90,"extra_data":92,"updated_unix":29},"fairpipes-data-mutation-pipelines-for-machine-learning-fairness","",{"@graph":37,"@context":87},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/fairpipes-data-mutation-pipelines-for-machine-learning-fairness/125905/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-25","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"What problem does FairPipes address in machine learning fairness?","Question",{"text":77,"@type":78},"FairPipes targets the limited understanding of how ML models respond to fairness-data perturbations after deployment, rather than only improving fairness using metrics and mitigation at the model level.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"How does FairPipes emulate fairness variations in data?",{"text":82,"@type":78},"FairPipes uses mutation operators that shuffle sensitive attributes, add new values, or modify their distribution to create fairness-related data variations.",{"name":84,"@type":75,"acceptedAnswer":85},"What do experiments on multiple models and datasets show?",{"text":86,"@type":78},"Results highlight different fairness sensitivity behaviors across models and indicate that model optimization affects fairness performance in a way that varies by model.","https://schema.org",{"og:url":53,"og:type":89,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":91,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":94},[95,99,103,107,112,117,121,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":96,"show_sort_weight":97,"slug":98},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Exam",70,"exam",{"id":108,"doc_module":4,"doc_module_name":47,"category_name":109,"show_sort_weight":110,"slug":111},5,"Comic",60,"comic",{"id":113,"doc_module":4,"doc_module_name":47,"category_name":114,"show_sort_weight":115,"slug":116},6,"Technology",50,"technology",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":30,"slug":122},"research-report",{"id":124,"doc_module":4,"doc_module_name":47,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":47,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":47,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":47,"category_name":137,"show_sort_weight":108,"slug":138},19,"General","general"]