[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123352-en":3,"doc-seo-123352-105":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},123352,962075114765,"Quinn","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Causal Machine Learning - Exploiting Changes for Generalization and Beyond - Dissertation","Causality is central to advancing machine learning beyond correlation-based approaches, supporting more robust, interpretable, and generalizable systems under distribution shifts. This dissertation studies causal representation learning by combining machine learning with causal inference to capture underlying causal mechanisms rather than relying on spurious correlations. It develops two approaches to address shifts and strengthen generalization, and connects machine learning with causal discovery to uncover deeper causal relationships. By integrating ML into causal discovery, the work improves predictive performance, enables better system design, and increases trustworthiness, while also supporting identification of relevant causal variables for applications including healthcare and biology.","Causal Machine Learning: Exploiting Changes for Generalization and Beyond  \nA Dissertation  \nPresented to the Faculty of the Graduate School of Cornell University  \nin Partial Fulfillment of the Requirements for the Degree of Doctor of Philosophy  \nby  \nBinh Minh Nguyen  \nDecember 2024  \n© 2024 Binh Minh Nguyen ALL RIGHTS RESERVED  \nCausal Machine Learning: Exploiting Changes for Generalization and Beyond  \nBinh Minh Nguyen, Ph.D.  \nCornell University 2024  \nCausality is crucial for advancing machine learning (ML) beyond correlation-based models, enabling more robust, interpretable, and generalizable systems. Understanding causal relationships helps improve decision-making, interventions, and predictions, especially in the presence of distribution shifts. Traditional ML models often fail in such settings, relying on spurious correlations rather than true causal structures. Causal representation learning, which combines ML with causal inference, offers a solution by capturing underlying causal mechanisms, enhancing model adaptability and robustness across domains.  \nThis thesis explores two approaches within causal representation learning to address distribution shifts and improve generalization. It also connects ML and causal discovery, aiming to uncover deeper causal relationships. By integrating ML techniques into causal discovery, we can improve model predictions, design better systems, and build more trustworthy AI. Additionally, causal discovery aids in identifying relevant causal variables, enhancing the effectiveness of causal representation learning in real-world applications like healthcare and biology.  \nBIOGRAPHICAL SKETCH  \nBinh Minh Nguyen earned his B.Eng. in Electrical Engineering in 2016, at the National University of Singapore. Around this time, he began doing research in Natural Language Processing with Dr. Nancy Chen at the Institute of InfoComm Research of A*Star Singapore. After graduation, Minh joined Prof. Thomas Yeo’s group at the National University of Singapore as a research assistant, applying machine learning techniques to answer neuroscience questions. This period of exploration strengthened his resolve to pursue graduate education. Before entering the Ph.D. program at Cornell University, Minh earned his M.S. in Computer Science at the University of CaliforniaDavis, working on dialog systems under the supervision of Prof. Zhou Yu.  \nAcknowledgements  \nNearing the end of my PhD journey, I can now proudly say that this has been the most memorable period in my life. Reaching this milestone would be impossible without the support I received from my mentors, collaborators, and friends.  \nFirst, I must thank my adviser Mert Sabuncu, who has helped me tremendously through this journey. Mert has given me great freedom to explore various research areas and has provided me with crucial advice when I ran into dead ends. Mert’s enthusiasm, belief, and research vision have propelled our research forward through the bleakest moments. I’m also very grateful for his patience and kindness, entertaining my countless late emails, last-minute requests, and impromptu meetings.  \nI also would like to thank many exceptional mentors whom I had the opportunity to interact with prior to my PhD. They have taught me many valuable lessons that I still draw on till this day. I learned from Nancy Chen the joy of doing research and the importance of developing a good taste for research problems. Nancy is my first mentor and I wouldn’t have ventured into research if it hadn’t been for her kindness and support. I learned about scientific rigor and the importance of thinking and communicating clearly from Thomas Yeo. Thomas is not only a brilliant researcher but also a dedicated teacher: I developed from a novice into a competent researcher under Thomas’ guidance. I learned the fundamentals of dialog systems from Zhou Yu. She also showed me the importance of execution speed. Ben Goh and Sharad Jaiswal showed me how to build complex ","cbCaidNWBr1q95Xs","https://ap.wps.com/l/cbCaidNWBr1q95Xs","pdf",3440234,1,111,"English","en",105,"# Abstract\n# BIOGRAPHICAL SKETCH\n# Acknowledgements\n# List of Figures\n# List of Tables\n# List of Abbreviations\n# 1 Introduction\n# 2 Robust Learning via Conditional Prevalence Adjustment\n## 2.1 Conditional Prevalence Adjustment (CoPA)\n## 2.2 Experiments\n## 2.3 Discussion\n# 3 A simple way to handle missing inputs\n## 3.1 Knockout\n## 3.2 Experiments\n## 3.3 Discussion\n# 4 Adapting to Shifting Correlations with Unlabeled Data Calibration\n## 4.1 Generalized Prevalence Adjustment (GPA)\n## 4.2 Experiments\n## 4.3 Discussion\n# 5 Efficient Id","[{\"question\":\"Why does the dissertation focus on causality instead of correlation-based machine learning?\",\"answer\":\"It argues that causality enables systems that are more robust, interpretable, and generalizable, particularly when data undergoes distribution shifts where correlations alone can be misleading.\"},{\"question\":\"What is causal representation learning in this work?\",\"answer\":\"It combines machine learning with causal inference to learn representations that reflect underlying causal mechanisms, improving adaptability and robustness across domains.\"},{\"question\":\"How does the thesis relate machine learning to causal discovery?\",\"answer\":\"It integrates machine learning techniques into causal discovery to improve predictions, design more effective systems, and identify relevant causal variables for real-world applications such as healthcare and biology.\"}]","Causal Machine Learning - Exploiting Changes for Generalization and Beyond - Dissertation | PDF",1785816080,280,{"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},"causal-machine-learning-exploiting-changes-for-generalization-and-beyond-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/causal-machine-learning-exploiting-changes-for-generalization-and-beyond-dissertation/123352/",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},"Why does the dissertation focus on causality instead of correlation-based machine learning?","Question",{"text":75,"@type":76},"It argues that causality enables systems that are more robust, interpretable, and generalizable, particularly when data undergoes distribution shifts where correlations alone can be misleading.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is causal representation learning in this work?",{"text":80,"@type":76},"It combines machine learning with causal inference to learn representations that reflect underlying causal mechanisms, improving adaptability and robustness across domains.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the thesis relate machine learning to causal discovery?",{"text":84,"@type":76},"It integrates machine learning techniques into causal discovery to improve predictions, design more effective systems, and identify relevant causal variables for real-world applications such as healthcare and biology.","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"]