[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117211-en":3,"doc-seo-117211-105":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},117211,5909877438554,"Maeve","https://ap-avatar.wpscdn.com/avatar/5600025385ad2bf12a7?_k=1778553567797529272",8,"Research & Report","Causality for Interpretable Machine Learning - Doctor of Philosophy Thesis","Machine learning adoption has expanded across domains such as image analysis, text categorization, predictive credit scoring, and recommendation systems, while concerns grow about the intrinsic “black-box” behavior of many models. This thesis addresses model interpretability by shifting focus from purely associative interpretability toward causal interpretation. It develops causal inference and counterfactual explanation methods, including a review of causal analysis techniques, dynamic propensity-score based causal inference, and two counterfactual strategies using causality-preserving safeguards and normalizing flows. It also targets counterfactual fairness via a min-max strategy for imperfect structural causal models.","UNIVERSITY OF TECHNOLOGY SYDNEY Faculty of Engineering and Information Technology  \nCausality for Interpretable Machine Learning  \nby  \nTri Dung Duong  \nA Thesis Submitted  \nin Fulfillment of the Requirements for the Degree  \nDoctor of Philosophy  \nSydney, Australia  \nCertificate of Original Authorship  \nI, Tri Dung Duong declare that this thesis, is submitted in fulfilment of the requirements for the award of Doctor of Philosophy, in the School of Computer Science, Faculty of Engineering and Information Technology at the University of Technology Sydney.  \nThis thesis is wholly my own work unless otherwise referenced or acknowledged. In addition, I certify that all information sources and literature used are indicated in the thesis.  \nThis document has not been submitted for qualifications at any other academic institution.  \nThis research is supported by the Australian Government Research Training Program.  \nSignature:  \nDate: 01 March 2023  \n© Copyright 2023 Tri Dung Duong  \nAbstract  \nThe past few years have borne witness to a marked surge in the adoption of machine learning (ML) techniques across a broad spectrum of fields, such as image analysis, text categorization, predictive credit scoring, and recommendation systems, among others. These techniques have made significant strides in various sectors, yet there is a growing concern among researchers about the “black-box” nature intrinsic to these methods. As a consequence, the need for interpreting machine learning models has taken center stage in scholarly debates. However, conventional approaches to machine learning interpretability have primarily focused on associative relationships rather than causal ones.  \nThis study seeks to bridge the existing gap in the causal interpretation of machine learning models by developing and enhancing both causal inference and counterfactual methodologies. Initially, it offers a comprehensive review of the causal analysis techniques utilized in machine learning models. Following this, the research proposes an innovative approach to causal inference, one that is anchored in the concept of dynamic propensity scores. In the context of counterfactual explanation, the study brings forward two strategies: one that prioritizes causality to safeguard the causal bonds within counterfactual instances, and another that utilizes a framework based on normalizing flows, designed to yield scalable and robust counterfactual samples. Concerning counterfactual fairness, the study aspires to formulate a min-max strategy designed to achieve counterfactual fairness even within an imperfect structural causal model. Collectively, this research is committed to enhancing the interpretability of machine learning models through the provision of causal explanations and counterfactual analyses.  \nTo my loved ones  \nAcknowledgments  \nCompleting a Ph.D. is a challenging endeavor that requires commitment, hard work, and a strong support system. Looking back on my journey, I am filled with gratitude for my supervisors, friends, and family, whose support was invaluable to my success. The task of writing this thesis was no small feat, and I wish to express my sincere thanks to those who have accompanied me on this journey.  \nFirstly, my heartfelt appreciation goes to my primary supervisor, Professor Guandong Xu, for his consistent support, motivation, and inspiration throughout my Ph.D. studies. His guidance has significantly contributed to my development as a researcher, and I am confident his mentorship will continue to impact my career positively. Despite the challenges brought about by the COVID-19 pandemic, Professor Xu’s guidance ensured that my research progress was not adversely affected. The experiences and skills I have gained under his supervision are invaluable, and these memories will be cherished.  \nA large part of this thesis is built upon peer-reviewed publications. I wish to express my gratitude to the anonymous reviewers whose feedback and suggestions g","cbCaideYigklcI67","https://ap.wps.com/l/cbCaideYigklcI67","pdf",6987857,1,189,"English","en",105,"# Abstract\n# Acknowledgments\n## Supervisors and reviewers\n## Friends and family\n# List of Publications\n## Published Papers","[{\"question\":\"What problem does the thesis target in machine learning interpretability?\",\"answer\":\"It targets the “black-box” nature of machine learning models and the limitation of conventional interpretability methods that rely mainly on associative relationships rather than causal ones.\"},{\"question\":\"How does the thesis propose causal inference for machine learning models?\",\"answer\":\"It proposes an approach anchored in dynamic propensity scores, after first reviewing causal analysis techniques used in machine learning.\"},{\"question\":\"What counterfactual explanation and fairness methods are introduced?\",\"answer\":\"It presents two counterfactual strategies: one that prioritizes causality to preserve causal bonds, and another based on normalizing flows to generate scalable and robust counterfactual samples, along with a min-max strategy for counterfactual fairness under imperfect structural causal models.\"}]","Causality for Interpretable Machine Learning - Doctor of Philosophy Thesis | PDF",1785674430,476,{"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},"causality-for-interpretable-machine-learning-doctor-of-philosophy-thesis","",{"@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/causality-for-interpretable-machine-learning-doctor-of-philosophy-thesis/117211/",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 thesis target in machine learning interpretability?","Question",{"text":75,"@type":76},"It targets the “black-box” nature of machine learning models and the limitation of conventional interpretability methods that rely mainly on associative relationships rather than causal ones.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the thesis propose causal inference for machine learning models?",{"text":80,"@type":76},"It proposes an approach anchored in dynamic propensity scores, after first reviewing causal analysis techniques used in machine learning.",{"name":82,"@type":73,"acceptedAnswer":83},"What counterfactual explanation and fairness methods are introduced?",{"text":84,"@type":76},"It presents two counterfactual strategies: one that prioritizes causality to preserve causal bonds, and another based on normalizing flows to generate scalable and robust counterfactual samples, along with a min-max strategy for counterfactual fairness under imperfect structural causal models.","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"]