[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119644-en":3,"doc-seo-119644-105":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},119644,13056703020460,"Valentina","https://ap-avatar.wpscdn.com/avatar/be000253dac470eee5d?_k=1778207105932848923",8,"Research & Report","HETEROGENEOUS MACHINE LEARNING WITH DECENTRALIZED DATA","This thesis investigates heterogeneous machine learning with decentralized data, where multiple clients with different data distributions jointly train or adapt models under a central server’s coordination while keeping private data on-device. It addresses three core problems: effective training across clients with heterogeneous labeled data, adaptive deployment to each target client without labels to handle distribution shifts, and robust system design resilient to random failures and malicious attacks. The work proposes client clustering for knowledge transfer, task-specific and collaborative test-time adaptation, and robust training and adaptation methods to reduce bias and out-of-distribution effects.","© 2025 Wenxuan Bao  \nHETEROGENEOUS MACHINE LEARNING WITH DECENTRALIZED DATA  \nBY  \nWENXUAN BAO  \nDISSERTATION  \nSubmitted in partial fulfillment of the requirements  \nfor the degree of Doctor of Philosophy in Computer Science  \nin the Graduate College of the  \nUniversity of Illinois Urbana-Champaign, 2025  \nUrbana, Illinois  \nDoctoral Committee:  \nProfessor Jingrui He, Chair  \nProfessor Tong Zhang  \nAssistant Professor Han Zhao  \nAssistant Professor Pan Li, Georgia Institute of Technology  \nABSTRACT  \nThis thesis explores heterogeneous machine learning with decentralized data, where multiple clients with distinct data distributions jointly train or adapt machine learning models under the coordination of a central server. Throughout the process, clients’ private data never leave their local devices. This paradigm underlies numerous real-world applications, such as collaborative training of financial fraud detection models among banks, or collective health monitoring enabled by massive wearable devices.  \nWe investigate three fundamental challenges in this setting. (P1) Effective model training: How can we train models from multiple source clients with heterogeneous labeled data so that models perform well across all clients? (P2) Adaptive model deployment: How can we adapt the trained model to each target client without labels, allowing it to adjust to its own data distribution for improved performance? (P3) Robust system design: How can we ensure robustness during both training and adaptation, preventing performance degradation caused by random failures or malicious attacks?  \nTo address (P1), we develop client clustering algorithms that enable knowledge transfer among clients with similar data distributions, allowing those with limited data to benefit from collaboration. For (P2), we first design task-specific adaptation algorithms that identify and mitigate distribution shifts across different modalities under one-to-one adaptation. We further extend to multi-client collaboration, where the model learns patterns of distribution shifts across clients to enable collaborative test-time adaptation. Finally, for (P3), we propose robust training algorithms resilient to abnormal or adversarial clients, and robust adaptation algorithms that mitigate model prediction bias and out-of-distribution data effects. Together, these contributions form an effective and robust framework for heterogeneous machine learning under decentralized data environments.  \nACKNOWLEDGMENTS  \nFirst and foremost, I would like to express my deepest gratitude to my advisor, Dr. Jingrui He, for her unwavering guidance, support, and encouragement throughout my Ph.D. journey. The early years of my doctoral study unfolded under the shadow of the COVID- 19 pandemic, when travel was restricted, communication was limited, and my first paper encountered multiple rejections. Facing difficulties in both life and research, Dr. He never gave up on me. Instead, she always believed in me, comforted me during setbacks, and encouraged me to move forward with optimism and persistence. Without her support, I would not have been able to complete my Ph.D. Dr. He has influenced me far beyond research itself. She is a true mentor in life, teaching me not only how to think critically and work rigorously, but also how to face challenges with courage and composure. Her famous advice,“Act like you want it!”, has become a personal motto that continually reminds me to take ownership of my goals and strive for excellence. At the same time, she also taught us the importance of balance: to slow down, relax, and appreciate life beyond research. These lessons, both in spirit and in practice, have had a profound and lasting impact on me, shaping the way I approach my career and life ahead.  \nI would also like to express my sincere appreciation to my thesis committee members, Dr. Pan Li, Dr. Tong Zhang, and Dr. Han Zhao, for their invaluable feedback and constructive suggestions, which signific","cbCaig4bb1pD8O8h","https://ap.wps.com/l/cbCaig4bb1pD8O8h","pdf",6277923,1,180,"English","en",105,"# Abstract\n## Problem Setting\n## Key Challenges (P1-P3)\n## Proposed Methods\n### P1: Effective Model Training\n### P2: Adaptive Model Deployment\n### P3: Robust System Design\n## Contributions Summary\n# Acknowledgments","[{\"question\":\"What is the decentralized heterogeneous machine learning setting studied in the thesis?\",\"answer\":\"Multiple clients with distinct data distributions coordinate training or adaptation with a central server, while private client data remains local and never leaves devices.\"},{\"question\":\"How does the thesis approach effective model training with heterogeneous labeled data?\",\"answer\":\"It develops client clustering algorithms to enable knowledge transfer among clients with similar data distributions so that clients with limited data can benefit from collaboration.\"},{\"question\":\"How is label-free adaptation performed on target clients?\",\"answer\":\"The thesis designs task-specific adaptation algorithms to identify and mitigate distribution shifts, then extends to multi-client collaboration for collaborative test-time adaptation by learning distribution-shift patterns across clients.\"}]","HETEROGENEOUS MACHINE LEARNING WITH DECENTRALIZED DATA | PDF",1785725442,454,{"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},"heterogeneous-machine-learning-with-decentralized-data","",{"@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/heterogeneous-machine-learning-with-decentralized-data/119644/",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","2026-08-03",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 is the decentralized heterogeneous machine learning setting studied in the thesis?","Question",{"text":75,"@type":76},"Multiple clients with distinct data distributions coordinate training or adaptation with a central server, while private client data remains local and never leaves devices.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the thesis approach effective model training with heterogeneous labeled data?",{"text":80,"@type":76},"It develops client clustering algorithms to enable knowledge transfer among clients with similar data distributions so that clients with limited data can benefit from collaboration.",{"name":82,"@type":73,"acceptedAnswer":83},"How is label-free adaptation performed on target clients?",{"text":84,"@type":76},"The thesis designs task-specific adaptation algorithms to identify and mitigate distribution shifts, then extends to multi-client collaboration for collaborative test-time adaptation by learning distribution-shift patterns across clients.","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"]