[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82716-en":3,"doc-seo-82716-105":29,"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":13,"seo_description":14,"update_tm":27,"read_time":28},82716,4810365810221,"Aurora","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Decentralised Federated Learning over Temporal Networks: The Role of Heterogeneities","Decentralised federated learning relies on peer-to-peer aggregation to enable privacy-preserving, communication-efficient training without a single-point failure. The influence of structural and temporal inhomogeneities in fully decentralised systems is still unclear. This work studies their effects when model parameters are locally averaged during aggregation, showing that early and stationary convergence follow the same dynamics as lazy random-walk diffusion on temporal networks. Typical experimental assumptions yield unrealistically fast convergence because they ignore inherent heterogeneities. Analysis of real-world temporal networks shows inhomogeneities often strongly slow diffusion and thus dominate convergence.","Decentralised Federated Learning over Temporal Networks: The Role of Heterogeneities  \nArash Badie-Modiri, Chiara Boldrini, Lorenzo Valerio, János Kertész and Márton Karsai  \narXiv :2607 .03 17 1v 1 [ cs .LG] 3 Jul 2026  \nAbstract—Decentralised federated learning, based on peerto-peer communication, is increasingly proposed for on-device training of machine learning models, promising a privacypreserving, communication-efficient training process with no risk of single-point failure. However, the role of structural and temporal inhomogeneities in such fully decentralised settings remains poorly understood. Here, we investigate their effects when model parameters are locally averaged during aggregation. We show that the decentralised federated learning process is governed, both in the early phase and the late, stationary limit, by the same dynamics as a lazy random-walk diffusion process on temporal networks. Based on this mapping, we demonstrate that the typical experimental scenario used in decentralised federated learning leads to unrealistically rapid convergence because of ignoring the temporal and structural inhomogeneities inherent in the communication network. We analyse real-world temporal networks and find that inhomogeneities most often dramatically slow down diffusion, hence the convergence process.  \nI. INTRODUCTION  \nDecentralised federated learning has emerged as a powerful paradigm for training machine learning models across entities without sharing raw data or requiring central coordination [1] . This approach is often studied in the context of data centres, for example in healthcare settings where multiple centres contribute patient data to jointly train a model without directly sharing sensitive information [2], [3] . However, decentralised federated learning can also be highly beneficial for end-user devices such as smartphones and internet-of-things devices [4] or autonomous vehicles [5], enabling them to contribute to model training using their local data without sharing raw and private data. Unlike the data-centre setting (where robust networking infrastructure allows reliable, persistent, and highbandwidth connections), edge devices communicate opportunistically: they go offline unpredictably, move through space, and may interact only when physical proximity or shared  \ninfrastructure allows. These constraints make the structure and timing of communications inherently irregular and heterogeneous.  \nEarly works addressed this setting under idealised assumptions of synchronous, peer-to-peer communication over simple network topologies [6], [7] . While more recent studies have begun to relax these assumptions by incorporating aspects of structural and temporal heterogeneity into the analysis [8]–[11], the forms considered remain narrow in scope. These  \nArash Badie-Modiri, Chiara Boldrini and Lorenzo Valerio are with the National Research Council, Pisa  \nArash Badie-Modiri, János Kertész and Márton Karsai are with the Central European University, Vienna  \nArash Badie-Modiri is with Aalto University, Espoo  \nMárton Karsai is with the HUN-REN Rényi Institute of Mathematics, Budapest  \nworks highlight the impact of features such as heterogeneous degree distributions, community structure, and intermittent communication failures on the convergence behaviour of decentralised learning systems. However, prior work largely treats heterogeneity as static topology variation (irregular but fixed graphs) or as one-shot randomly induced disruption, such as links or nodes deactivated independently at random. Neither of these captures the richer dynamics present in real-world temporal networks, where communication patterns may be bursty, temporally correlated, and shaped by memory-bearing processes that couple structure and timing in non-trivial ways.  \nIn parallel, the network science literature has developed a rich theoretical understanding of dynamical processes on complex networks, including diffusion and spreading on sy","cbCaivdThbreWTc6","https://ap.wps.com/l/cbCaivdThbreWTc6","pdf",544219,1,15,"English","en",105,"# Introduction\n## Decentralised federated learning in edge and IoT settings\n## Motivation: limitations of prior heterogeneity models\n## Bridging learning dynamics with temporal-network diffusion\n# Methodology and main contributions\n## Mapping learning to diffusion on temporal networks\n## Early phase vs stationary regime analyses\n## Validation on synthetic and real-world temporal contact networks\n# Key findings","[{\"question\":\"What question does the study address about decentralised federated learning?\",\"answer\":\"It investigates how structural and temporal inhomogeneities affect convergence when model parameters are aggregated through local averaging in fully decentralised settings.\"},{\"question\":\"How does the work connect learning dynamics to a network-science concept?\",\"answer\":\"It models decentralised federated learning as a diffusion process on a temporal communication network, where parameter dissemination is governed by lazy random-walk diffusion dynamics.\"},{\"question\":\"Why can common decentralised federated learning experiments converge unrealistically fast?\",\"answer\":\"Because they typically ignore the temporal and structural inhomogeneities present in real communication networks, which otherwise slow diffusion and convergence.\"}]",1784182467,38,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"decentralised-federated-learning-over-temporal-networks-the-role-of-heterogeneities","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/decentralised-federated-learning-over-temporal-networks-the-role-of-heterogeneities/82716/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-21","2026-07-16",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 question does the study address about decentralised federated learning?","Question",{"text":75,"@type":76},"It investigates how structural and temporal inhomogeneities affect convergence when model parameters are aggregated through local averaging in fully decentralised settings.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the work connect learning dynamics to a network-science concept?",{"text":80,"@type":76},"It models decentralised federated learning as a diffusion process on a temporal communication network, where parameter dissemination is governed by lazy random-walk diffusion dynamics.",{"name":82,"@type":73,"acceptedAnswer":83},"Why can common decentralised federated learning experiments converge unrealistically fast?",{"text":84,"@type":76},"Because they typically ignore the temporal and structural inhomogeneities present in real communication networks, which otherwise slow diffusion and convergence.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"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":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":45,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":45,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]