[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122431-en":3,"doc-seo-122431-105":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":20,"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},122431,13056703019662,"Evangeline","https://ap-avatar.wpscdn.com/avatar/be000253a8e92610077?_k=1778726343310543188",8,"Research & Report","Enhanced Collaboration In between the Machine Learning Models - Bringing Decentralized Learning to Reality - Dissertation","Opportunistic mobile social networks formed through everyday spontaneous interactions create new opportunities for machine learning at the edge. As mobile computation grows, model training can be offloaded from centralized servers to edge devices, better matching individuals’ dynamic needs than federated or traditional centralized learning. This dissertation studies decentralized machine learning in opportunistic mobile social networks, emphasizing privacy, scalability, cost reduction, and resilience to single points of failure.","Copyright by  \nHaoxiang Yu 2025  \n1  \nThe Dissertation Committee for Haoxiang Yu certifies that this is the approved version of the following dissertation:  \nEnhanced Collaboration In between the Machine Learning Models: Bringing Decentralized Learning to Reality  \nCommittee:  \nHaris Vikalo, Supervisor Christine Julien, Co-supervisor Xi Zheng  \nEdison Thomaz  \nBrian Evans  \nEnhanced Collaboration In between the Machine Learning Models: Bringing Decentralized Learning to Reality  \nby  \nHaoxiang Yu  \nDissertation  \nPresented to the Faculty of the Graduate School of The University of Texas at Austin  \nin Partial Fulfillment  \nof the Requirements  \nfor the Degree of  \nDoctor of Philosophy  \nThe University of Texas at Austin August 2025  \nDedication  \nTo my family and friends who supported me through this journey.  \nAcknowledgments  \nNo one completes a PhD alone. Every step forward—especially the small, hard-won ones—was made possible by people who offered guidance, patience, and faith. I am deeply grateful to you all.  \nFirst and foremost, I thank my advisors, Dr. Christine Julien and Dr. Haris Vikalo. You both gave me direction without prescribing the destination, paired freedom with high standards, and offered steady encouragement when the path was unclear—gifts that have shaped not only this thesis, but also how I will approach research and mentorship in the years ahead. I am grateful to my committee—Dr. Xi Zheng, Dr. Edison Thomaz, and Dr. Brian Evans—for your thoughtful questions and rigorous feedback. Your critiques pushed me to make my arguments sharper, my experiments cleaner, and my writing more precise.  \nTo my labmates, classmates, and friends: thank you for your steadfast support. You taught me how to collaborate under uncertainty and celebrate progress that doesn’t fit neatly into a results table. I thank our collaborators and the many people who keep the wheels turning behind the scenes—colleagues across projects, the staff at UT Austin, and my internship mentors. Your professionalism and kindness made difficult work possible. I’m grateful to my early mentors—Dr. Vaskar Raychoudhuryand Dr. Md Osman Gani—for their guidance.  \nMy deepest thanks go to my family. To my parents, Bingshi Yu and Min Han, and to my extended family—thank you for your unwavering love and for valuing effort and integrity over outcomes. If my grandmother could read this, I hope she would see that I have tried to live up to the hopes she had for me.  \nThese years have taught me to be patient with complexity and persistent in the face of imperfect answers. Whatever comes next, I will carry forward the care, rigor, and generosity I learned from you.  \nThank you for helping me become the researcher—and person—I am today.  \nAbstract  \nEnhanced Collaboration In between the Machine Learning Models: Bringing Decentralized Learning to Reality  \nHaoxiang Yu, PhD  \nThe University of Texas at Austin, 2025  \nSUPERVISORS: Haris Vikalo, Christine Julien  \nOpportunistic mobile social networks, formed through the spontaneous interactions of mobile devices as individuals engage in daily life, present unique opportunities for machine learning applications. Historically, due to computational limitations, machine learning tasks have been conducted on powerful centralized computers rather than on edge devices. Nowadays, as computational resources on mobile devices continue to increase, it has become feasible to offload model training onto these edge devices. Training and improving models within these existing opportunistic mobile social networks aligns more closely with individuals’ dynamic needs compared to federated learning and traditional centralized learning. This thesis explores aspects of decentralized machine learning within opportunistic mobile social networks as a promising alternative learning process. Decentralized learning architectures enhance privacy and scalability, align with dynamically changing environments, reduce infrastructure costs, and are res","cbCaik3NjbFBqKxs","https://ap.wps.com/l/cbCaik3NjbFBqKxs","pdf",6753628,1,125,"English","en",105,"# List of Tables\n# List of Figures\n# Chapter 1: Introduction\n# Chapter 2: Related Works\n## 2.1 Centralized vs. Distributed Machine Learning\n## 2.2 Pervasive and Ubiquitous Computing\n## 2.3 Other technologies","[{\"question\":\"Why does the dissertation focus on opportunistic mobile social networks?\",\"answer\":\"It argues that daily, spontaneous device interactions create unique settings where machine learning can run effectively on edge resources while aligning with individuals’ evolving needs.\"},{\"question\":\"How does the thesis connect decentralized learning with privacy and scalability?\",\"answer\":\"It highlights that decentralized learning architectures improve privacy, scalability, reduce infrastructure costs, and avoid single points of failure compared with centralized approaches.\"},{\"question\":\"What three main technical directions does the dissertation investigate?\",\"answer\":\"It examines blockchain-based incentive mechanisms, digital-twin-enabled decentralized learning for ephemeral encounter opportunities, and mobility-driven model sharing using devices as “mules” for continuous aggregation and customization.\"}]","Enhanced Collaboration In between the Machine Learning Models - Bringing Decentralized Learning to Reality - Dissertation | PDF",1785810599,315,{"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},"enhanced-collaboration-in-between-the-machine-learning-models-bringing-decentralized-learning-to-reality-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/enhanced-collaboration-in-between-the-machine-learning-models-bringing-decentralized-learning-to-reality-dissertation/122431/",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":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why does the dissertation focus on opportunistic mobile social networks?","Question",{"text":75,"@type":76},"It argues that daily, spontaneous device interactions create unique settings where machine learning can run effectively on edge resources while aligning with individuals’ evolving needs.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the thesis connect decentralized learning with privacy and scalability?",{"text":80,"@type":76},"It highlights that decentralized learning architectures improve privacy, scalability, reduce infrastructure costs, and avoid single points of failure compared with centralized approaches.",{"name":82,"@type":73,"acceptedAnswer":83},"What three main technical directions does the dissertation investigate?",{"text":84,"@type":76},"It examines blockchain-based incentive mechanisms, digital-twin-enabled decentralized learning for ephemeral encounter opportunities, and mobility-driven model sharing using devices as “mules” for continuous aggregation and customization.","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"]