[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118920-en":3,"doc-seo-118920-105":30,"detail-sidebar-cat-0-en-105":92},{"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},118920,1649267921044,"Ava Thompson","https://us-avatar.wpscdn.com/avatar/1800007509477c92dfb?_k=1782875107921204101",8,"Research & Report","Decentralized and Collaborative Machine Learning Framework for IoT","Decentralized machine learning is explored as a way to address security limitations of canonical federated learning. The paper introduces a decentralized and collaborative machine learning framework designed for resource-constrained IoT devices. It defines key construction blocks including a prototype-based incremental learning algorithm tailored for low-performance elements, two random-based protocols for exchanging local models, and two algorithmic approaches for prediction and prototype creation. The framework is evaluated against a centralized incremental learning baseline on accuracy, training time, and robustness, reporting promising results.","Computer Networks 239 (2024) 110137  \n| Decentralized and collaborative machine learning framework for IoT✩ Martín González-Sotoa,b,∗, Rebeca P. Díaz-Redondo a, Manuel Fernández-Veiga a, Bruno Fernández-Castrob, Ana Fernández-Vilasa\u003Cbr>a atlanTTic - I&C Lab - Universidade de Vigo, Escola de Enxeñaría de Telecomunicación Campus Univesitario, Vigo, 36310, Spain\u003Cbr>b Centro Tecnolóxico de Telecomunicacións de Galicia (GRADIANT), Carretera do Vilar, 56 -58, Vigo, 36214, Spain |  |  |  |\n| --- | --- | --- | --- |\n| A R T I C L E I N F O |  | A B S T R A C T |  |\n| Keywords:\u003Cbr>Incremental learning Decentralized learning Federated learning |  | Decentralized machine learning has recently been proposed as a potential solution to the security issues of the canonical federated learning approach. In this paper, we propose a decentralized and collaborative machine learning framework specially oriented to resource-constrained devices, usual in IoT deployments. With this aim we propose the following construction blocks. First, an incremental learning algorithm based on prototypes that was specifically implemented to work in low-performance computing elements. Second, two random-based protocols to exchange the local models among the computing elements in the network. Finally, two algorithmics approaches for prediction and prototype creation. This proposal was compared toa typical centralized incremental learning approach in terms of accuracy, training time and robustness with very promising results. |  |\n\n1. Introduction  \nDecentralized machine learning faces how to use data and models from different sources to build machine learning models that gather the partial knowledge learned by each agent in this network to create, in a collaborative way, a global vision or model of the whole network. This would allow processing large amount of data managed by different computing elements. However, this approach entails several issues that must be considered when proposing solutions for this kind of computing environments. One of the most worrying is how to provide secure and private solutions that protect personal data when building global models.  \nSome approaches have been already proposed to decentralize machine learning algorithms so that a set of networked agents can participate in building a global model. Among them, the best known is federated learning [1,2]. This approach is based on a hierarchic organization where a master computing element receives information from other computing nodes in the network. The latter only share information of the local model, but they do not share local data. The master element combines these models to obtain a global one that is sent back to all computing nodes. However, there have been arisen other alternatives [3,4] that omit the central server and try to provide a decentralized network, having the well-known advantages of not having a central point of failure and potential attacks.  \nAdditionally to these efforts to provide more robust and efficient decentralized architectures for machine learning, there are aspects that must be taken into account when selecting the algorithmics for these collaborative scenarios. The philosophy of incremental learning [5–7] or online learning is a relevant approach that refers to the continuous and adaptive learning of an algorithm. These algorithms focus on creating models that can continuously learn as new unobserved samples are introduced to the model from any data stream or source. Thus, incremental learning allows a model to evolve and react to perceived changes in its environment dynamically. However, it must be noticed that this approach implies that the learning process must rely on more compact representations, under memory limitation scenarios [5].  \nThe ability of a machine-learning algorithm to incrementally learn as new data becomes available is a characteristic that allows machinelearning algorithms to be more suitable for many current real-life problems such","cbCaikbMJ4jcuI3b","https://ap.wps.com/l/cbCaikbMJ4jcuI3b","pdf",4272314,1,12,"English","en",105,"# Introduction\n## Decentralized machine learning vs federated learning\n## Incremental (online) learning and memory constraints\n## IoT motivation: incremental data and hybrid Cloud–Fog–Mist architectures","[{\"question\":\"Why does the paper consider decentralized machine learning instead of standard federated learning?\",\"answer\":\"Decentralized machine learning is considered as a potential solution to security issues in canonical federated learning, while avoiding a central point of failure and reducing exposure to certain attack scenarios.\"},{\"question\":\"What are the main components proposed by the framework?\",\"answer\":\"The paper proposes a prototype-based incremental learning algorithm for low-performance devices, two random-based protocols to exchange local models, and algorithmic approaches for prediction and prototype creation.\"},{\"question\":\"How is the proposed approach evaluated?\",\"answer\":\"It is compared with a typical centralized incremental learning approach using metrics such as accuracy, training time, and robustness, with results that are described as very promising.\"}]","Decentralized and Collaborative Machine Learning Framework for IoT | PDF",1785720953,30,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"decentralized-and-collaborative-machine-learning-framework-for-iot","",{"@graph":36,"@context":86},[37,54,69],{"@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/decentralized-and-collaborative-machine-learning-framework-for-iot/118920/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04","2026-08-03",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why does the paper consider decentralized machine learning instead of standard federated learning?","Question",{"text":76,"@type":77},"Decentralized machine learning is considered as a potential solution to security issues in canonical federated learning, while avoiding a central point of failure and reducing exposure to certain attack scenarios.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What are the main components proposed by the framework?",{"text":81,"@type":77},"The paper proposes a prototype-based incremental learning algorithm for low-performance devices, two random-based protocols to exchange local models, and algorithmic approaches for prediction and prototype creation.",{"name":83,"@type":74,"acceptedAnswer":84},"How is the proposed approach evaluated?",{"text":85,"@type":77},"It is compared with a typical centralized incremental learning approach using metrics such as accuracy, training time, and robustness, with results that are described as very promising.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":29,"slug":122},"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":107,"slug":138},19,"General","general"]