{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T05:19:07Z","timestamp":1740028747335,"version":"3.37.3"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2106891","2107062"],"award-info":[{"award-number":["2106891","2107062"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF CAREER Award","doi-asserted-by":"publisher","award":["2340482"],"award-info":[{"award-number":["2340482"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006754","name":"ARL","doi-asserted-by":"publisher","award":["W911NF-23-2-0014"],"award-info":[{"award-number":["W911NF-23-2-0014"]}],"id":[{"id":"10.13039\/100006754","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Signal Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tsp.2025.3526782","type":"journal-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:47:06Z","timestamp":1737053226000},"page":"766-780","source":"Crossref","is-referenced-by-count":0,"title":["Empowering Federated Learning With Implicit Gossiping: Mitigating Connection Unreliability Amidst Unknown and Arbitrary Dynamics"],"prefix":"10.1109","volume":"73","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5958-132X","authenticated-orcid":false,"given":"Ming","family":"Xiang","sequence":"first","affiliation":[{"name":"Department of ECE, Northeastern University, Boston, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8355-4751","authenticated-orcid":false,"given":"Stratis","family":"Ioannidis","sequence":"additional","affiliation":[{"name":"Department of ECE, Northeastern University, Boston, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9544-1567","authenticated-orcid":false,"given":"Edmund","family":"Yeh","sequence":"additional","affiliation":[{"name":"Department of ECE, Northeastern University, Boston, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0785-9291","authenticated-orcid":false,"given":"Carlee","family":"Joe-Wong","sequence":"additional","affiliation":[{"name":"Department of ECE, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3538-5679","authenticated-orcid":false,"given":"Lili","family":"Su","sequence":"additional","affiliation":[{"name":"Department of ECE, Northeastern University, Boston, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC49753.2023.10383258"},{"key":"ref2","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Artif. Intell. Statist.","author":"McMahan","year":"2017"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1561\/9781680837896"},{"key":"ref4","article-title":"On the convergence of fedavg on non-iid data","author":"Li","year":"2020","journal-title":"Int. Conf. Learn. Represent."},{"article-title":"Bidirectional compression in heterogeneous settings for distributed or federated learning with partial participation: tight convergence guarantees","year":"2020","author":"Philippenko","key":"ref5"},{"key":"ref6","article-title":"A unified analysis of federated learning with arbitrary client participation","author":"Wang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","first-page":"374","article-title":"Towards federated learning at scale: System design","volume-title":"Proc. Mach. Learn. Syst.","volume":"1","author":"Bonawitz","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3152445"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2018.1701370"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOMW.2019.8845191"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761718"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3224590"},{"key":"ref13","first-page":"234","article-title":"Distributed delayed stochastic optimization","volume":"24","author":"Agarwal","year":"2011","journal-title":"Ad. Neural Inf. Process. Syst."},{"key":"ref14","first-page":"251","article-title":"Asynchronous parallel stochastic gradient for nonconvex optimization","volume":"28","author":"Lian","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9303830"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2525015"},{"key":"ref17","first-page":"111","article-title":"A tight convergence analysis for stochastic gradient descent with delayed updates","volume-title":"Algorithmic Learning Theory","author":"Arjevani","year":"2020"},{"issue":"1","key":"ref18","first-page":"9613","article-title":"The error-feedback framework: Better rates for sgd with delayed gradients and compressed updates","volume":"21","author":"Stich","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref19","first-page":"25331","article-title":"Anarchic federated learning","volume-title":"Int. Conf. Mach. Learn.","author":"Yang","year":"2022"},{"key":"ref20","first-page":"12052","article-title":"Fast federated learning in the presence of arbitrary device unavailability","volume":"34","author":"Gu","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796818"},{"key":"ref22","first-page":"10351","article-title":"Towards understanding biased client selection in federated learning","volume-title":"Int. Conf. Artif. Intell. Statist.","author":"Cho","year":"2022"},{"key":"ref23","first-page":"5677","article-title":"On the convergence of federated averaging with cyclic client participation","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","volume":"202","author":"Cho","year":"2023"},{"key":"ref24","article-title":"Optimal client sampling for federated learning","author":"Chen","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref25","first-page":"3403","article-title":"Towards flexible device participation in federated learning","volume-title":"Int. Conf. Artif. Intell. Statist.","author":"Ruan","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.2022.0057.cd"},{"key":"ref27","article-title":"A lightweight method for tackling unknown participation statistics in federated averaging","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang","year":"2024"},{"key":"ref28","first-page":"906","article-title":"Fedvarp: Tackling the variance due to partial client participation in federated learning","volume-title":"Proc. 38th Conf. Uncertainty Artif. Intell., Mach. Learn. Res.","volume":"180","author":"Jhunjhunwala","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM53939.2023.10228873"},{"key":"ref30","first-page":"7611","article-title":"Tackling the objective inconsistency problem in heterogeneous federated optimization","volume":"33","author":"Wang","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/SFCS.2003.1238221"},{"issue":"58","key":"ref32","article-title":"Robust asynchronous stochastic gradient-push: Asymptotically optimal and network-independent performance for strongly convex functions","volume":"21","author":"Spiridonoff","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref33","first-page":"5132","article-title":"Scaffold: Stochastic controlled averaging for federated learning","volume-title":"Int. Conf. Mach. Learn.","author":"Karimireddy","year":"2020"},{"key":"ref34","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume-title":"Proc. Mach. Learn. Syst.","volume":"2","author":"Li","year":"2020"},{"key":"ref35","article-title":"On convergence of fedprox: Local dissimilarity invariant bounds, non-smoothness and beyond","author":"Yuan","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Federated learning in the presence of adversarial client unavailability","year":"2024","author":"Su","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2022.3212536"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/62212.62234"},{"article-title":"Achieving linear speedup with partial worker participation in non-IID federated learning","year":"2021","author":"Yang","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1137\/070704277"},{"article-title":"Reading digits in natural images with unsupervised feature learning","year":"2011","author":"Netzer","key":"ref41"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref42"},{"article-title":"Cinic-10 is not imagenet or cifar-10","year":"2018","author":"Darlow","key":"ref43"},{"article-title":"Measuring the effects of non-identical data distribution for federated visual classification","year":"2019","author":"Hsu","key":"ref44"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11750-007-0018-z"},{"key":"ref46","first-page":"361","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["IEEE Transactions on Signal Processing"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/78\/10807692\/10843736-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/78\/10807692\/10843736.pdf?arnumber=10843736","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,19]],"date-time":"2025-02-19T19:09:53Z","timestamp":1739992193000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10843736\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/tsp.2025.3526782","relation":{},"ISSN":["1053-587X","1941-0476"],"issn-type":[{"type":"print","value":"1053-587X"},{"type":"electronic","value":"1941-0476"}],"subject":[],"published":{"date-parts":[[2025]]}}}