[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-116955-en":3,"doc-seo-116955-105":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},116955,34359740700684,"Finn","https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487",8,"Research & Report","Investigating Trade-offs For Fair Machine Learning Systems - Doctor of Philosophy Dissertation","Fairness in software systems enables nondiscriminatory algorithm behavior with respect to protected attributes such as gender, race, and age. Ensuring fairness is a critical non-functional requirement for data-driven machine learning. Bias-mitigation approaches can reduce discrimination, yet they often introduce performance deterioration. This dissertation examines the trade-offs practitioners face when debiasing machine learning systems, including literature review, benchmarking for evaluating fairness–performance trade-offs, a proposed post-processing debiasing method, and an empirical study on handling fairness with respect to age thresholds.","Investigating Trade-offs For Fair Machine Learning Systems  \nMax Hort  \nA dissertation submitted in partial fulfillment of the requirements for the degree of  \nDoctor of Philosophy  \nof  \nUniversity College London.  \nDepartment of Computer Science  \nUniversity College London  \nJanuary 27, 2023  \n2  \nI, Max Hort, confirm that the work presented in this thesis is my own. Where information has been derived from other sources, I confirm that this has been indicated in the work. I list below the chapters based on publications:  \nChapter 3  \n• Max Hort, Zhenpeng Chen, Jie M Zhang, Federica Sarro, and Mark Harman. Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey. arXiv  \npreprint arXiv:2207.07068, 2022  \nChapter 4  \n• Max Hort, Jie M. Zhang, Federica Sarro, and Mark Harman. Fairea: A Model Behaviour Mutation Approach to Benchmarking Bias Mitigation Methods. In Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 2021  \nChapter 5  \n• Max Hort, Jie M Zhang, Federica Sarro, and Mark Harman. Search-based Automatic Repair for Fairness and Accuracy in Decision-making Software. Under review, 2022  \nChapter 6  \n• Max Hort and Federica Sarro. Privileged and Unprivileged Groups: An Empirical Study on the Impact of the Age Attribute on Fairness. In International Workshop on Equitable Data and Technology (FairWare '22) . ACM, 2022  \nAdditional Articles  \nAdditionally, I co-authored the following articles, which are not included in this thesis:  \n1. Zhenpeng Chen, Jie M Zhang, Max Hort, Federica Sarro, and Mark Harman. Fairness testing: A comprehensive survey and analysis of trends. arXiv preprint arXiv:2207.10223, 2022  \n2. Max Hort and Federica Sarro. The Effect of Offspring Population Size on NSGA-II: A Preliminary Study. In Proceedings of the 2021 Genetic and Evolutionary Computation Conference Companion, 2021  \n3  \n3. Max Hort, Maria Kechagia, Federica Sarro, and Mark Harman. A Survey of Performance Optimization for Mobile Applications. IEEE Transactions on Software Engineering (TSE), 2021  \n4. Max Hort and Federica Sarro. Optimising Word Embeddings With Search-Based Approaches. In Proceedings of the 2020 Genetic and Evolutionary Computation Conference Companion, pages 269–270, 2020  \n5. Emeralda Sesari, Max Hort, and Federica Sarro. An Empirical Study on the Fairness of Pre-trained Word Embeddings. In Proceedings of the 4th Workshop on Gender Bias in Natural Language Processing, 2022  \n6. James Zhong, Max Hort, and Federica Sarro. Py2Cy: A Genetic Improvement Tool To Speed Up Python. In Genetic and Evolutionary Computation Conference Companion (GECCO '22 Companion), 2022  \n7. Max Hort, Rebecca Moussa, and Federica Sarro. Multi-objective search for gender-fair and semantically correct word embeddings. Applied Soft Computing, 133:109916, 2023  \n8. Minghua Ma, Zhao Tian, Max Hort, Federica Sarro, Hongyu Zhang, Qingwei Lin, and Dongmei Zhang. Enhanced fairness testing via generating effective initial individual discriminatory instances. arXiv preprint arXiv:2209.08321, 2022  \n9. Max Hort and Federica Sarro. Did You Do Your Homework? Raising Awareness on Software Fairness and Discrimination. In 2021 36th IEEE/ACM International Conference on Automated Software Engineering (ASE) , pages 1322–1326 . IEEE, 2021  \nAbstract  \nFairness in software systems aims to provide algorithms that operate in a nondiscriminatory manner, with respect to protected attributes such as gender, race, or age. Ensuring fairness is a crucial non-functional property of data-driven Machine Learning systems. Several approaches (i.e., bias mitigation methods) have been proposed in the literature to reduce bias of Machine Learning systems. However, this often comes hand in hand with performance deterioration. Therefore, this thesis addresses trade-offs that practitioners face when debiasing Machine Learning systems.  \nAt first, we perform a literature review to investig","cbCaihIOVD1uh6ht","https://ap.wps.com/l/cbCaihIOVD1uh6ht","pdf",7807485,1,200,"English","en",105,"# Abstract\n## Fairness and bias mitigation trade-offs\n## Literature review and evaluation overview\n## Benchmarking approach for bias mitigation\n## Proposed debiasing method and post-processing\n## Empirical study on age-based fairness","[{\"question\":\"What problem does the dissertation focus on regarding fair machine learning systems?\",\"answer\":\"It focuses on the trade-offs practitioners face when debiasing machine learning systems, where improving fairness often coincides with performance deterioration.\"},{\"question\":\"What are the dissertation’s main contributions?\",\"answer\":\"It includes a literature review of debiasing techniques, a benchmarking approach to compare bias mitigation methods and their trade-offs, and a proposed post-processing debiasing method to improve both fairness and accuracy.\"},{\"question\":\"How does the thesis address fairness with respect to age?\",\"answer\":\"It evaluates how to deal with age-related fairness using empirical results on real-world datasets, including examining different age thresholds.\"}]","Investigating Trade-offs For Fair Machine Learning Systems - Doctor of Philosophy Dissertation | PDF",1785672825,504,{"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},"investigating-trade-offs-for-fair-machine-learning-systems-doctor-of-philosophy-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/investigating-trade-offs-for-fair-machine-learning-systems-doctor-of-philosophy-dissertation/116955/",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","2026-08-02",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 focus on regarding fair machine learning systems?","Question",{"text":75,"@type":76},"It focuses on the trade-offs practitioners face when debiasing machine learning systems, where improving fairness often coincides with performance deterioration.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What are the dissertation’s main contributions?",{"text":80,"@type":76},"It includes a literature review of debiasing techniques, a benchmarking approach to compare bias mitigation methods and their trade-offs, and a proposed post-processing debiasing method to improve both fairness and accuracy.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the thesis address fairness with respect to age?",{"text":84,"@type":76},"It evaluates how to deal with age-related fairness using empirical results on real-world datasets, including examining different age thresholds.","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"]