[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119026-en":3,"doc-seo-119026-105":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},119026,137441390410,"Hazel","https://ap-avatar.wpscdn.com/avatar/2000252f4ab5702993?_k=1776741390130283984",8,"Research & Report","Decentralised and collaborative machine learning framework for IoT - Research report","Decentralised machine learning is presented as a security-oriented alternative to canonical federated learning, targeting common constraints in IoT deployments. The framework is built from incremental prototype-based learning adapted for low-performance computing elements, paired with two random-based protocols for exchanging local models. Two algorithmic approaches are provided for prediction and prototype creation. Experiments compare the proposal to centralized incremental learning in accuracy, training time, and robustness, reporting very promising results.","arXiv :2312 . 12190v1 [ cs .LG] 19 Dec 2023  \nDecentralised and collaborative machine  \nlearning framework for IoT  \nMart´ın Gonzlez-Soto and Rebeca P. D´ıaz-Redondo and Manuel Fernndez-Veiga and Bruno  \nRodr´ıguez-Castro and Ana Fernndez-Vilas  \nAbstract  \nDecentralised 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 decentralised 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 to a typical centralized incremental learning approach in terms of accuracy, training time and robustness with very promising results.  \nI. 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 decentralise machine learning algorithms so that a set of networked agents can participate in building a global model. Among them, the best known is federated  \natlanTTic -I&C Lab -Universidade de Vigo  \nThis is an extension of the conference paper ”XuILVQ: A River Implementation of the Incremental Learning Vector Quantization for IoT”, DOI: [https://doi.org/10.1145/3551663.3558676](https://doi.org/10.1145/3551663.3558676) .  \nDecember 20, 2023 DRAFT  \nlearning [1], [2] . This approach is based on a hierarchic organisation 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 decentralised 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 decentralised 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], [6],[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 machine-learning algorithms to be more suitable for many current real-life problems such as data analysis and big data processing in data streaming scenarios, robotic","cbCaiargFnHdHxs0","https://ap.wps.com/l/cbCaiargFnHdHxs0","pdf",1324798,1,26,"English","en",105,"# Abstract\n# Introduction\n## Background: federated vs decentralised learning\n## Incremental/online learning for data streams in IoT\n## Proposed collaborative decentralised architecture\n# Contributions\n## XuILVQ adaptation for resource-constrained devices\n## Network mechanisms: Fully ILVQ and Hybrid approaches","[{\"question\":\"Why does the paper propose decentralised machine learning instead of canonical federated learning?\",\"answer\":\"It is proposed as a potential solution to security issues in the canonical federated learning approach, while also supporting decentralised operation without a central point.\"},{\"question\":\"What problem does incremental learning address in IoT scenarios?\",\"answer\":\"Incremental learning enables continuous and adaptive model updates as new unobserved samples arrive, which suits data streaming and dynamic environments common in IoT.\"},{\"question\":\"How is the incremental learning algorithm adapted for resource-constrained IoT devices?\",\"answer\":\"The paper adapts ILVQ into a resource-aware implementation named XuILVQ, including adding a class prediction mechanism and adjusting the threshold distance computation.\"}]","Decentralised and collaborative machine learning framework for IoT - Research report | PDF",1785721982,66,{"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},"decentralised-and-collaborative-machine-learning-framework-for-iot-research-report","",{"@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/decentralised-and-collaborative-machine-learning-framework-for-iot-research-report/119026/",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 propose decentralised machine learning instead of canonical federated learning?","Question",{"text":76,"@type":77},"It is proposed as a potential solution to security issues in the canonical federated learning approach, while also supporting decentralised operation without a central point.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What problem does incremental learning address in IoT scenarios?",{"text":81,"@type":77},"Incremental learning enables continuous and adaptive model updates as new unobserved samples arrive, which suits data streaming and dynamic environments common in IoT.",{"name":83,"@type":74,"acceptedAnswer":84},"How is the incremental learning algorithm adapted for resource-constrained IoT devices?",{"text":85,"@type":77},"The paper adapts ILVQ into a resource-aware implementation named XuILVQ, including adding a class prediction mechanism and adjusting the threshold distance computation.","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},[94,98,102,106,111,116,121,124,129,132,136],{"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":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]