[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123163-en":3,"doc-seo-123163-105":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},123163,7971461740909,"Levi","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Fairness specification and repair for machine learning pipeline - dissertation","Fairness specification and repair for machine learning pipeline studies how to formalize fairness requirements and automatically mitigate bias in end-to-end machine learning workflows without sacrificing predictive performance. The dissertation develops performance-aware repair strategies using AutoML, including dynamic optimization and efficient search-space pruning for bias elimination. It further introduces fairness contracts and a modular fairness checker that validate fairness specifications across pipeline components. Extensive evaluations measure effectiveness, adaptability, efficiency, and applicability under multiple research questions.","Fairness specification and repair for machine learning pipeline  \nby  \nGiang Nguyen  \nA dissertation submitted to the graduate faculty  \nin partial fulfillment of the requirements for the degree of  \nDOCTOR OF PHILOSOPHY  \nMajor: Computer Science  \nProgram of Study Committee:  \nHridesh Rajan, Co-major Professor  \nWei Le, Co-major Professor  \nYing Cai  \nGurpur Prabhu  \nQi Li  \nSimanta Mitra  \nThe student author, whose presentation of the scholarship herein was approved by the program of study committee, is solely responsible for the content of this dissertation. The Graduate College will ensure this dissertation is globally accessible and will not permit alterations after a degree is  \nconferred.  \nIowa State University  \nAmes, Iowa  \n2024  \nCopyright © Giang Nguyen, 2024 . All rights reserved.  \nii  \nDEDICATION  \nI would like to dedicate this thesis to my family without whose support I would not have been able to complete this work.  \niii  \nTABLE OF CONTENTS  \nPage  \n[LIST OF TABLES .......................................... vi](LIST OF TABLES .......................................... vi)  \n[LIST OF FIGURES ......................................... viii](LIST OF FIGURES ......................................... viii)  \n[ACKNOWLEDGMENTS ...................................... ix](ACKNOWLEDGMENTS ...................................... ix)  \n[ABSTRACT ............................................. xi](ABSTRACT ............................................. xi)  \n[CHAPTER 1. GENERAL INTRODUCTION .......................... 1](CHAPTER 1. GENERAL INTRODUCTION .......................... 1)  \n[1.1 Contribution ........................................ 4](1.1 Contribution ........................................ 4)  \n[1.2 Background & Related Work ............................... 5](1.2 Background & Related Work ............................... 5)  \n1.2.1 Fairness in ML Pipeline .............................. 5  \n1.2.2 Software Engineering for ML Fairness ...................... 9  \nBibliography ........................................... 10  \nCHAPTER 2. FIX FAIRNESS, DON’T RUIN ACCURACY: PERFORMANCE AWARE FAIRNESS REPAIR USING AUTOML ............................ 18  \n2.1 Abstract ........................................... 18  \n2.2 Introduction ......................................... 19  \n2.3 Background ......................................... 21  \n2.3.1 Preliminaries .................................... 21  \n2.3.2 Related Work .................................... 23  \n2.4 Motivation ......................................... 24  \n2.5 Problem Definition ..................................... 27  \n2.6 Fair-AutoML ........................................ 29  \n2.6.1 Dynamic Optimization for Bias Elimination ................... 29  \n2.6.2 Search Space Pruning for Efficient Bias Elimination .............. 32  \n2.7 Evaluation .......................................... 36  \n2.7.1 Experiment ..................................... 37  \n2.7.2 Effectiveness (RQ1) ................................ 39  \n2.7.3 Adaptability (RQ2) ................................ 42  \n2.7.4 Ablation Study (RQ3) ............................... 45  \n2.8 Discussion .......................................... 47  \n2.9 Threats to Validity ..................................... 48  \n2.10 Conclusion ......................................... 49  \nBibliography ........................................... 49  \niv  \nCHAPTER 3. DESIGN BY FAIRNESS CONTRACT FOR MACHINE LEARNING PIPELINE 58  \n3.1 Abstract ........................................... 58  \n3.2 Introduction ......................................... 59  \n3.3 Motivation ......................................... 61  \n3.4 Problem Formulation .................................... 63  \n3.4.1 Classification Program ............................... 63  \n3.4.2 ML Pipeline ..................................... 63  \n3.4.3 Fairness Specification ............................... 64  \n3.5 Guidelines for Writing, Collecting, and Using Fairness Con","cbCaibycDpBmLO4A","https://ap.wps.com/l/cbCaibycDpBmLO4A","pdf",1816558,1,150,"English","en",105,"# CHAPTER 1. GENERAL INTRODUCTION\n## 1.1 Contribution\n## 1.2 Background & Related Work\n# CHAPTER 2. FIX FAIRNESS, DON’T RUIN ACCURACY: PERFORMANCE AWARE FAIRNESS REPAIR USING AUTOML\n## 2.6 Fair-AutoML\n## 2.7 Evaluation","[{\"question\":\"What problem does the dissertation address in ML pipelines?\",\"answer\":\"It addresses how to specify fairness requirements and repair pipelines to reduce bias while maintaining accuracy and overall performance.\"},{\"question\":\"How does Fair-AutoML aim to improve bias elimination?\",\"answer\":\"It uses dynamic optimization to eliminate bias and employs search space pruning to make the repair process more efficient.\"},{\"question\":\"What are fairness contracts used for?\",\"answer\":\"Fairness contracts provide guidelines and formal specifications for writing, collecting, and using fairness requirements, which can be checked and applied throughout the pipeline.\"}]","Fairness specification and repair for machine learning pipeline - dissertation | PDF",1785814986,378,{"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},"fairness-specification-and-repair-for-machine-learning-pipeline-dissertation","",{"@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/fairness-specification-and-repair-for-machine-learning-pipeline-dissertation/123163/",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 problem does the dissertation address in ML pipelines?","Question",{"text":75,"@type":76},"It addresses how to specify fairness requirements and repair pipelines to reduce bias while maintaining accuracy and overall performance.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does Fair-AutoML aim to improve bias elimination?",{"text":80,"@type":76},"It uses dynamic optimization to eliminate bias and employs search space pruning to make the repair process more efficient.",{"name":82,"@type":73,"acceptedAnswer":83},"What are fairness contracts used for?",{"text":84,"@type":76},"Fairness contracts provide guidelines and formal specifications for writing, collecting, and using fairness requirements, which can be checked and applied throughout the pipeline.","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"]