{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:06:28Z","timestamp":1776888388884,"version":"3.51.2"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643685489","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T00:00:00Z","timestamp":1729036800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,16]]},"abstract":"<jats:p>Federated learning algorithms, such as FedAvg, are negatively affected by data heterogeneity and partial client participation. To mitigate the latter problem, global variance reduction methods, like FedVARP, leverage stale model updates for non-participating clients. These methods are effective under homogeneous client participation. Yet, this paper shows that, when some clients participate much less than others, aggregating updates with different levels of staleness can detrimentally affect the training process. Motivated by this observation, we introduce FedStale, a novel algorithm that updates the global model in each round through a convex combination of \u201cfresh\u201d updates from participating clients and \u201cstale\u201d updates from non-participating ones. By adjusting the weight in the convex combination, FedStale interpolates between FedAvg, which only uses fresh updates, and FedVARP, which treats fresh and stale updates equally. Our analysis of FedStale convergence yields novel findings: i)\u00a0it integrates and extends previous FedAvg and FedVARP analyses to heterogeneous client participation; ii)\u00a0it underscores how the least participating client influences convergence error; iii)\u00a0it provides practical guidelines to best exploit stale updates, showing that their usefulness diminishes as data heterogeneity decreases and participation heterogeneity increases. Extensive experiments featuring diverse levels of client data and participation heterogeneity not only confirm these findings but also show that FedStale outperforms both FedAvg and FedVARP in many settings.1 1 A preprint version of this paper, including supplementary material, is available.<\/jats:p>","DOI":"10.3233\/faia240849","type":"book-chapter","created":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T13:32:43Z","timestamp":1729171963000},"source":"Crossref","is-referenced-by-count":3,"title":["FedStale: leveraging Stale Updates in Federated Learning"],"prefix":"10.3233","author":[{"given":"Angelo","family":"Rodio","sequence":"first","affiliation":[{"name":"Centre Inria d\u2019Universit\u00e9 C\u00f4te d\u2019Azur, France. Email: {firstname.lastname}@inria.fr"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Giovanni","family":"Neglia","sequence":"additional","affiliation":[{"name":"Centre Inria d\u2019Universit\u00e9 C\u00f4te d\u2019Azur, France. Email: {firstname.lastname}@inria.fr"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","ECAI 2024"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA240849","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T13:32:44Z","timestamp":1729171964000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA240849"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,16]]},"ISBN":["9781643685489"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia240849","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,16]]}}}