[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120077-en":3,"doc-seo-120077-105":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},120077,2336464648322,"Aria","https://ap-avatar.wpscdn.com/avatar/2200025388227c56fec?_k=1778556882303663488",8,"Research & Report","Enhancing Federated Learning Efficiency through Dynamic Model Adaptation and Optimization","Federated learning (FL) in cloud computing enables decentralized, scalable machine learning while confronting key obstacles in communication efficiency and data privacy. This thesis proposes a dynamic federated learning framework that improves efficiency via model compression, PCA-based dimensionality reduction, and fine-tuning. The number of PCA components is selected according to client data variability, while pruning and quantization reduce communication without degrading accuracy. Fine-tuning serves as knowledge distillation to address skewness and overfitting. Evaluation uses communication cost, bandwidth utilization, and latency across MNIST and CIFAR-10 under varying data skewness.","KORRAPATI, BHUVANA, M.S. Enhancing Federated Learning Efficiency through Dynamic Model Adaptation and Optimization. (2024)  \nDirected by Dr. Jing Deng. 88 pp.  \nFederated learning (FL) in cloud computing has emerged as a groundbreaking paradigm, revolutionizing data processing and machine learning through decentralized and scalable systems. However, the integration of these technologies faces challenges in communication efficiency and data privacy preservation, which are crucial for their widespread adoption and effectiveness. This research presents a dynamic federated learning approach that incorporates model compression, PCA-based dimensionality reduction, and fine-tuning to address these challenges.  \nThe proposed method dynamically determines the optimal number of PCA components based on client data variability, effectively reducing data dimensionality. By applying model compression techniques, including pruning and quantization, the approach enhances communication efficiency without compromising the performance. Furthermore, the integration of fine-tuning as a knowledge distillation step allows the compressed models to adapt to client-specific data patterns, thereby tackling issues of skewness and overfitting.  \nIn addressing the challenges of bandwidth and latency in FL, the evaluation metrics encompass Average Communication Cost, Average Bandwidth Utilization, and Average Latency, demonstrating the approach’s effectiveness in optimizing these key performance indicators. Moreover, the framework incorporates dynamic model adaptation on both client-side and server-side, enabling personalized adjustments based on local data characteristics and client resources, while optimizing the global model’s performance.  \nUsing both the MNIST and CIFAR-10 datasets for validation, this approach  \ndemonstrates maintained accuracy with data reduction across various levels of data skewness and complexity. The proposed federated learning framework follows a comprehensive flow chart that encompasses server initialization, model distribution, client-side processing (including data dimensionality reduction, model compression, local training, fine-tuning, and dynamic adaptation), server-side aggregation, global model update, model evaluation, and iterative refinement. This research contributes to the advancing field of cloud-based FL by presenting an efficient, privacy-preserving, and scalable approach for distributed machine learning, setting a new standard for optimizing communication efficiency in decentralized data environments and paving the way for the next generation of federated learning systems that prioritize efficiency, privacy, and scalability.  \nENHANCING FEDERATED LEARNING EFFICIENCY THROUGH DYNAMIC MODEL ADAPTATION AND OPTIMIZATION  \nby  \nBhuvana Korrapati  \nA Thesis Submitted to  \nthe Faculty of The Graduate School at  \nThe University of North Carolina at Greensboro  \nin Partial Fulfillment  \nof the Requirements for the Degree  \nMaster of Science  \nGreensboro  \n2024  \nApproved by  \nCommittee Chair  \nTo my parents for their continual support of my academic career.  \nii  \nAPPROVAL PAGE  \nThis thesis written by Bhuvana Korrapati has been approved by the following committee of the Faculty of The Graduate School at The University of North Carolina at Greensboro.  \nCommittee Chair   Jing Deng  \nCommittee Members    \nMinjeong Kim  \nQianqian Tong  \nDate of Acceptance by Committee  \nDate of Final Oral Examination  \nACKNOWLEDGMENTS  \nI would like to thank my advisor, Jing Deng, for helping me to prepare this Thesis. His experience and advise were invaluable.  \nPREFACE  \nIn this research, we explore the dynamic integration of Federated Machine Learning (FL) and cloud computing, focusing particularly on optimizing communication efficiency through adaptive model modifications. Our study introduces innovative methodologies that include dynamic data reduction and model compression techniques, tailored to the variability in client data. These ","cbCaifTqZr1moIbV","https://ap.wps.com/l/cbCaifTqZr1moIbV","pdf",1462582,1,103,"English","en",105,"# Introduction\n## Overview\n## Federated vs Traditional Approach\n## Centralized Learning vs Federated Learning\n# Related Work\n## Federated Learning Applications\n### Healthcare\n### Self-Driving Cars\n### Mobile Edge Computing\n### Internet of Things\n### Information Technology\n## Federated Learning Privacy\n### Privacy Attacks\n### Differential Privacy (DP)\n### Secure Multi-Party Computation (SMPC)\n### Federated Transfer Learning (FTL)\n## Federated Learning Communication Efficiency\n### Federated Dropout\n### Structured and Sketched Updates\n## Communication Challenges in Federated Learning\n### FedSCR: Structure-Based Communication Reduction for Federated Learning","[{\"question\":\"What problem does the thesis address in federated learning systems?\",\"answer\":\"It targets communication efficiency limitations and the need to preserve data privacy while enabling scalable decentralized machine learning in cloud environments.\"},{\"question\":\"How does the proposed approach reduce communication overhead?\",\"answer\":\"It combines PCA-based dimensionality reduction with model compression methods such as pruning and quantization to lower the amount of data exchanged.\"},{\"question\":\"How does fine-tuning improve performance after compression?\",\"answer\":\"Fine-tuning is integrated as a knowledge distillation step so compressed models adapt to client-specific data patterns, helping mitigate skewness and overfitting.\"}]","Enhancing Federated Learning Efficiency through Dynamic Model Adaptation and Optimization | PDF",1785728022,260,{"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},"enhancing-federated-learning-efficiency-through-dynamic-model-adaptation-and-optimization","",{"@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/enhancing-federated-learning-efficiency-through-dynamic-model-adaptation-and-optimization/120077/",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":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the thesis address in federated learning systems?","Question",{"text":75,"@type":76},"It targets communication efficiency limitations and the need to preserve data privacy while enabling scalable decentralized machine learning in cloud environments.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed approach reduce communication overhead?",{"text":80,"@type":76},"It combines PCA-based dimensionality reduction with model compression methods such as pruning and quantization to lower the amount of data exchanged.",{"name":82,"@type":73,"acceptedAnswer":83},"How does fine-tuning improve performance after compression?",{"text":84,"@type":76},"Fine-tuning is integrated as a knowledge distillation step so compressed models adapt to client-specific data patterns, helping mitigate skewness and overfitting.","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"]