[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121927-en":3,"doc-seo-121927-105":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},121927,549758252649,"Ivy","https://ap-avatar.wpscdn.com/avatar/8000253669c5317157?_k=1778319167496531819",8,"Research & Report","Advances In Explainable Artificial Intelligence, Fair Machine Learning, And The Intersections Thereof","Artificial intelligence (AI) can improve human life through automation, yet machine learning (ML) carries risks that limit reliable use in sensitive domains. ML systems learn by optimizing complex non-linear mappings, which often makes models difficult to interpret and vulnerable to error, misuse, and harmful bias. Explainable artificial intelligence (XAI) and fair machine learning aim to improve transparency and reduce unfair outcomes, but existing methods leave important limitations unaddressed. This dissertation advances XAI and fairness by proposing approaches that explain full models, extend explanations beyond supervised learning, and explore alternatives to input-space explanations.","UC Davis  \nUC Davis Electronic Theses and Dissertations  \nTitle  \nAdvances In Explainable Artificial Intelligence, Fair Machine Learning, And The Intersections Thereof  \nPermalink  \n[https://escholarship.org/uc/item/6rx3v80b](https://escholarship.org/uc/item/6rx3v80b)  \nAuthor  \nLivanos, Michael  \nPublication Date  \n2024  \nPeer reviewed|Thesis/dissertation  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nAdvances In Explainable Artificial Intelligence, Fair Machine Learning, And The Intersections Thereof  \nBy  \nMICHAEL J. LIVANOS  \nDISSERTATION  \nSubmitted in partial satisfaction of the requirements for the degree of DOCTOR OF PHILOSOPHY  \nin  \nCOMPUTER SCIENCE  \nin the  \nOFFICE OF GRADUATE STUDIES  \nof the  \nUNIVERSITY OF CALIFORNIA  \nDAVIS  \nApproved:  \n\n| Ian Davidson, Chair |\n| --- |\n| Hamed Pirsiavash |\n\nJiawei Zhang Committee in Charge 2024  \n© Michael J. Livanos, 2024 . All rights reserved.  \nDedicated to my barking dog, Delilah  \nii  \nContents  \nAbstract vii  \nAcknowledgments viii  \nChapter 1 . Introduction 1  \n1.1. Limitations Of Existing Explainable AI 2  \n1.2. Limitations Of Existing Fair Machine Learning 3  \n1.3. Our Contributions 4  \n1.4. Summary Of The Dissertation 6  \nChapter 2 . Cooperative Knowledge Distillation: A Learner Agnostic Approach 10  \n2.1. Introduction 10  \n2.2. Related Work 12  \n2.3. Our Approach: Cooperative Distillation 14  \n2.4. Experiments 18  \n2.5. Understanding The Mechanisms of Distillation 24  \n2.6. Discussion & Conclusion 25  \nChapter 3 . Model Agnostic Relative Explanations for Anomaly Detection Using Diverse Counterfactuals 27  \n3.1. Introduction 27  \n3.2. Related Work & The Need For XAD 30  \n3.3. Problem Overview & Definition 32  \n3.4. Our Approach To Finding Explanation Vectors 34  \n3.5. Experimental Design 37  \n3.6. Experimental Results 41  \n3.7. Conclusion and Future Work 46  \nChapter 4 . An Exemplars-Base Approach for Explainable Clustering: Complexity and Efficient Approximation Algorithms 48  \n4.1. Introduction 48  \n4.2. Overview of Our Approach 50  \n4.3. Definitions 52  \n4.4. Algorithmic Results 55  \n4.5. Experiments 58  \n4.6. Related Work 63  \n4.7. Conclusions 63  \nChapter 5 . Identification and Uses of Deep Learning Backbones via Pattern Mining 65  \n5.1. Introduction 65  \n5.2. Overview of Our Approach 68  \n5.3. Problem Definition and ILP Formulation 69  \n5.4. Approach 72  \n5.5. Models and Datasets 75  \n5.6. Experimental Design 75  \n5.7. Experiments 77  \n5.8. Reproducibility Details: Model Architecture and Dataset Selection 80  \n5.9. Related Work 81  \n5.10. Conclusion 82  \nChapter 6 . The Intersectional Unfairness Paradox: An Empirical Investigation Of Intersectional Fairness 83  \n6.1. Introduction 83  \n6.2. Approach 85  \n6.3. Results & Conclusion 86  \nChapter 7 . Foundations Of Unfairness in Anomaly Detection-Case Studies in Facial Imaging Data 88  \n7.1. Introduction 88  \n7.2. Background and Related Work 90  \n7.3. Four Reasons for Unfairness And Their Measurement 91  \n7.4. Experimental Results-Who Is AD Unfair To? 96  \n7.5. Experimental Results-Why is AD Unfair 98  \n7.6. Discussion and Conclusion 105  \nChapter 8 . Beyond Data Bias: Proof of Algorithmic Fairness Challenges in Neural Networks 108  \n8.1. Proof 108  \n8.2. Approximation To Expected Fairness 113  \n8.3. Empirical Evaluation Of Integral 115  \n8.4. Conclusion 118  \nChapter 9 . (Un)fair Backbones In Neural Network 119  \n9.1. Introduction 119  \n9.2. Related Work & Backbones 121  \n9.3. Approach 122  \n9.4. Experimental Results 126  \n9.5. Conclusion 129  \nChapter 10 . Conclusion 131  \nAppendix A. An Exemplars-Base Approach for Explainable Clustering: Complexity and Efficient Approximation Algorithms-Proofs, Runtimes, & Exemplars 132  \nA.1 . Additional Material for Section 4.3 132  \nA.2 . Additional Material for Section 4.4 133  \nA.3 . Additional Material for Section 4.5 137  \nA.4 . Additional Material for Section 4.6 139  \nAppendix B. Identification & uses of Deep ","cbCaib7bcsz7u2iw","https://ap.wps.com/l/cbCaib7bcsz7u2iw","pdf",9878667,1,175,"English","en",105,"# Chapter 1 . Introduction\n## Limitations Of Existing Explainable AI\n## Limitations Of Existing Fair Machine Learning\n## Our Contributions\n## Summary Of The Dissertation\n# Chapter 2 . Cooperative Knowledge Distillation: A Learner Agnostic Approach\n## Our Approach: Cooperative Distillation\n## Experiments\n## Understanding The Mechanisms of Distillation\n## Discussion & Conclusion\n# Chapter 3 . Model Agnostic Relative Explanations for Anomaly Detection Using Diverse Counterfactuals\n## Related Work & The Need For XAD\n## Problem Overview & Definition\n## Experimental Design\n## Experimental Results\n## Conclusion and Future Work\n# Chapter 4 . An Exemplars-Base Approach for Explainable Clustering: Complexity and Efficient Approximation Algorithms\n## Overview of Our Approach\n## Algorithmic Results\n## Experiments\n## Conclusions\n# Chapter 5 . Identification and Uses of Deep Learning Backbones via Pattern Mining\n## Overview of Our Approach\n## Problem Definition and ILP Formulation\n## Approach\n## Experimental Design\n## Reproducibility Details: Model Architecture and Dataset Selection\n## Conclusion\n# Chapter 6 . The Intersectional Unfairness Paradox: An Empirical Investigation Of Intersectional Fairness\n## Approach\n## Results & Conclusion\n# Chapter 7 . Foundations Of Unfairness in Anomaly Detection-Case Studies in Facial Imaging Data\n## Four Reasons for Unfairness And Their Measurement\n## Experimental Results-Who Is AD Unfair To?\n## Experimental Results-Why is AD Unfair\n## Discussion and Conclusion\n# Chapter 8 . Beyond Data Bias: Proof of Algorithmic Fairness Challenges in Neural Networks\n## Proof\n## Approximation To Expected Fairness\n## Empirical Evaluation Of Integral\n## Conclusion\n# Chapter 9 . (Un)fair Backbones In Neural Network\n## Approach\n## Experimental Results\n## Conclusion\n# Chapter 10 . Conclusion","[{\"question\":\"What problem does the dissertation address regarding machine learning in sensitive domains?\",\"answer\":\"Machine learning models can be hard to interpret and can produce error, misuse, or harmful bias, which restricts safe applicability in high-stakes settings.\"},{\"question\":\"How does the dissertation advance explainable artificial intelligence (XAI)?\",\"answer\":\"It develops approaches that explain the entire model (not only individual actions), creates techniques for ML tasks beyond supervised learning, and studies alternatives to input-space explanations.\"},{\"question\":\"What is the dissertation’s focus on fairness, and how is it investigated?\",\"answer\":\"It targets unfair or biased outcomes in ML systems, including intersectional unfairness and unfairness in anomaly detection, using empirical investigations and measurement of contributing factors.\"}]","Advances In Explainable Artificial Intelligence, Fair Machine Learning, And The Intersections Thereof | PDF",1785807786,441,{"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},"advances-in-explainable-artificial-intelligence-fair-machine-learning-and-the-intersections-thereof","",{"@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/advances-in-explainable-artificial-intelligence-fair-machine-learning-and-the-intersections-thereof/121927/",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 regarding machine learning in sensitive domains?","Question",{"text":75,"@type":76},"Machine learning models can be hard to interpret and can produce error, misuse, or harmful bias, which restricts safe applicability in high-stakes settings.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the dissertation advance explainable artificial intelligence (XAI)?",{"text":80,"@type":76},"It develops approaches that explain the entire model (not only individual actions), creates techniques for ML tasks beyond supervised learning, and studies alternatives to input-space explanations.",{"name":82,"@type":73,"acceptedAnswer":83},"What is the dissertation’s focus on fairness, and how is it investigated?",{"text":84,"@type":76},"It targets unfair or biased outcomes in ML systems, including intersectional unfairness and unfairness in anomaly detection, using empirical investigations and measurement of contributing factors.","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"]