[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123838-en":3,"doc-seo-123838-105":30,"detail-sidebar-cat-0-en-105":83},{"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},123838,4398048949847,"Eliana","https://ap-avatar.wpscdn.com/avatar/400002536579ef2da7f?_k=1778318612642679267",8,"Research & Report","Fuzzy-based Augmentation of Federated Averaging for Enhanced Decentralized Machine Learning","Federated Averaging (FedAvg) supports decentralized machine learning with a strong focus on data privacy, yet it is hindered by non-IID data, communication bottlenecks, and susceptibility to adversarial attacks. The proposed fuzzy-based FedAvg introduces fuzzy logic to model uncertainty and improve aggregation in decentralized settings. Fuzzy clustering adapts the model to diverse data distributions, while fuzzy membership functions apply adaptive weights to enhance convergence and accuracy. Privacy-preserving protection is integrated via homomorphic encryption and differential privacy, and simulations indicate improved convergence, robustness to non-IID data, and stronger privacy versus traditional FedAvg.","Fuzzy-based Augmentation of Federated Averaging for Enhanced Decentralized Machine  \nLearning  \nSisir Kumar Rajbongshi1* , Kshirod Sarmah2* , Bikram Patir3, Swapnanil Gogoi4 and Satyajit Sarmah5  \n1Department of Computer Science, Pandit Deendayal Upadhyaya Adarsha Mahavidyalaya (A Govt. Model College),  \nGoalpara, 783124, Assam, India [sisirrajbongshi@gmail.com](sisirrajbongshi@gmail.com)  \n2Department of Computer Science, Pandit Deendayal Upadhyaya Adarsha Mahavidyalaya (A Govt. Model College),  \nGoalpara, 783124, Assam, [India kshirodsarmah@gmail.com](India kshirodsarmah@gmail.com)  \n3Department of Computer Science, PDUAM,Dalgaon,784116 Assam, [India bikrampatir15@gmail.com](India bikrampatir15@gmail.com)[ ](India bikrampatir15@gmail.com)4GUCDOE, Gauhati University, Guwahati-781014, Assam, [India swapnanil@gauhati.ac.in](India swapnanil@gauhati.ac.in)[ ](India swapnanil@gauhati.ac.in)5Department of Information Technology, Gauhati University, Guwahati-781014, Assam, [India ss@gauhati.ac.in](India ss@gauhati.ac.in)  \n*Corresponding Authors: Sisir Kumar Rajbongshi and Kshirod Sarmah  \n*Department of Computer Science, Pandit Deendayal Upadhyaya Adarsha Mahavidyalaya (A Govt. Model College), Goalpara, 783124, Assam, India, [sisirrajbongshi@gmail.com](sisirrajbongshi@gmail.com) , [kshirodsarmah@gmail.com](kshirodsarmah@gmail.com)  \nAbstract:  \nFederated Averaging (FedAvg) is a leading decentralized machine learning approach, prioritizing data privacy. However, it faces challenges like non-identically distributed data, communication bottlenecks, and adversarial attacks. This abstract introduces a fuzzy-based FedAvg, leveraging fuzzy logic to manage uncertainty in decentralized environments. Fuzzy clustering adapts the model to varied data distributions, addressing non-IID challenges. Fuzzy membership functions enhance aggregation by introducing an adaptive weighting scheme, improving convergence and accuracy. The fuzzy approach incorporates privacy-preserving mechanisms, ensuring secure aggregation with homomorphic encryption and differential privacy. Simulations show improved convergence, resilience to non-IID data, and enhanced privacy compared to traditional FedAvg, contributing to more secure decentralized ML systems.  \n1. Introduction  \nIn the rapidly evolving landscape of decentralized machine learning (ML), Federated Averaging (FedAvg) has emerged as a cornerstone, offering a promising avenue for model training while prioritizing the critical aspect of data privacy. However, conventional FedAvg methods grapple with multifaceted challenges, including non-identically distributed data, communication bottlenecks, and susceptibility to adversarial attacks. This research responds to these challenges by introducing an innovative and adaptive approach—fuzzy-based Federated Averaging—designed to elevate both the robustness and privacy considerations within decentralized ML frameworks. Harnessing the power of fuzzy logic, our proposed fuzzy FedAvg navigates the inherent uncertainties and imprecisions that characterize real-world decentralized environments. Fuzzy clustering techniques, seamlessly integrated into our approach, empower the model to dynamically adapt to the diverse data distributions across participating devices. This adaptation mitigatesthe adverse effects of non-identically distributed data, offering a more resilient and responsive solution to the challenges posed by decentralized datasets.  \nAdditionally, the incorporation of fuzzy membership functions introduces a nuanced weighting scheme during the aggregation process, enhancing the convergence speed and accuracy of the global model. Federated learning (FL) is a privacy-preserving distributed machine learning (ML) paradigm [1] . In FL, a central server connects with enormous clients (e.g., mobile phones etc.); the clients keep their data without sharing it with the server. In each communication round, clients receive the current global model from the server, and a sm","cbCaiunPheMk12Ic","https://ap.wps.com/l/cbCaiunPheMk12Ic","pdf",328383,1,7,"English","en",105,"# Abstract\n# Introduction\n## Federated learning overview\n## Challenges in FedAvg and decentralized FL","[{\"question\":\"How is privacy preserved in the proposed approach?\",\"answer\":\"Privacy-preserving mechanisms combine secure aggregation using homomorphic encryption with differential privacy to protect sensitive local information.\"}]","Fuzzy-based Augmentation of Federated Averaging for Enhanced Decentralized Machine Learning | PDF",1785818824,18,{"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":78,"head_meta":80,"extra_data":82,"updated_unix":28},"fuzzy-based-augmentation-of-federated-averaging-for-enhanced-decentralized-machine-learning","",{"@graph":36,"@context":77},[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/fuzzy-based-augmentation-of-federated-averaging-for-enhanced-decentralized-machine-learning/123838/",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],{"name":72,"@type":73,"acceptedAnswer":74},"How is privacy preserved in the proposed approach?","Question",{"text":75,"@type":76},"Privacy-preserving mechanisms combine secure aggregation using homomorphic encryption with differential privacy to protect sensitive local information.","Answer","https://schema.org",{"og:url":52,"og:type":79,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":81,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":84},[85,89,93,97,102,107,111,114,119,122,126],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":86,"show_sort_weight":87,"slug":88},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":90,"show_sort_weight":91,"slug":92},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Exam",70,"exam",{"id":98,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},5,"Comic",60,"comic",{"id":103,"doc_module":4,"doc_module_name":46,"category_name":104,"show_sort_weight":105,"slug":106},6,"Technology",50,"technology",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":112,"slug":113},30,"research-report",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":98,"slug":129},19,"General","general"]