{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,17]],"date-time":"2026-01-17T08:04:41Z","timestamp":1768637081989,"version":"3.49.0"},"reference-count":79,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62473098"],"award-info":[{"award-number":["62473098"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DE250100961"],"award-info":[{"award-number":["DE250100961"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Netw. Sci. Eng."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tnse.2025.3648495","type":"journal-article","created":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T18:24:41Z","timestamp":1766773481000},"page":"5539-5550","source":"Crossref","is-referenced-by-count":0,"title":["EF21 With Momentum and Partial Participation for Non-Convex Federated Learning Under Biased Compression"],"prefix":"10.1109","volume":"13","author":[{"given":"Xiaohe","family":"Wang","sequence":"first","affiliation":[{"name":"School of Cyber Science and Engineering, Engineering Research Center of Blockchain Application, Supervision and Management, Ministry of Education, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4443-608X","authenticated-orcid":false,"given":"Xinli","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Engineering Research Center of Blockchain Application, Supervision and Management, Ministry of Education, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0070-8597","authenticated-orcid":false,"given":"Guanghui","family":"Wen","sequence":"additional","affiliation":[{"name":"School of Automation, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8093-9787","authenticated-orcid":false,"given":"Xinghuo","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Engineering, RMIT University, Melbourne, VIC, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Federated learning: Strategies for improving communication efficiency","volume-title":"Proc. NIPS Workshop Private Multi-Party Mach. Learn.","author":"Konen","year":"2016"},{"key":"ref2","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"McMahan","year":"2017"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2020.106854"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-020-00323-1"},{"key":"ref5","article-title":"Federated learning for mobile keyboard prediction","author":"Hard","year":"2018"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3439228"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2022.3206243"},{"key":"ref8","first-page":"1756","article-title":"Communication complexity of distributed convex learning and optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Arjevani","year":"2015"},{"key":"ref9","article-title":"Deep gradient compression: Reducing the communication bandwidth for distributed training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lin","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1561\/9781680837896"},{"key":"ref11","article-title":"Local SGD converges fast and communicates little","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Stich","year":"2019"},{"key":"ref12","first-page":"5132","article-title":"Scaffold: Stochastic controlled averaging for federated learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Karimireddy","year":"2020"},{"key":"ref13","first-page":"560","article-title":"signSGD: Compressed optimisation for non-convex problems","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bernstein","year":"2018"},{"key":"ref14","first-page":"2387","article-title":"Preserved central model for faster bidirectional compression in distributed settings","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Philippenko","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796982"},{"key":"ref16","article-title":"Federated optimization algorithms with random reshuffling and gradient compression","author":"Sadiev","year":"2022"},{"key":"ref17","first-page":"47626","article-title":"Delta: Diverse client sampling for fasting federated learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Wang","year":"2023"},{"issue":"288","key":"ref18","first-page":"1","article-title":"Compressed and distributed least-squares regression: Convergence rates with applications to federated learning","volume":"25","author":"Philippenko","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref19","first-page":"6292","article-title":"Communication-compressed adaptive gradient method for distributed nonconvex optimization","volume-title":"Proc. Int. Conf. Artif. Intell. Stat.","author":"Wang","year":"2022"},{"key":"ref20","first-page":"1707","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alistarh","year":"2017"},{"key":"ref21","first-page":"9872","article-title":"ATOMO: Communication-efficient learning via atomic sparsification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Wang","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/473"},{"issue":"276","key":"ref23","first-page":"1","article-title":"On biased compression for distributed learning","volume":"24","author":"Beznosikov","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref24","first-page":"4452","article-title":"Sparsified SGD with memory","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Stich","year":"2018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2020.3042094"},{"key":"ref26","first-page":"16752","article-title":"${ST}_{k}$ : A scalable module for solving top-k problems","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Xia","year":"2024"},{"key":"ref27","first-page":"11450","article-title":"Communication-efficient distributed blockwise momentum SGD with error-feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Zheng","year":"2019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2023.3280938"},{"key":"ref29","first-page":"3252","article-title":"Error feedback fixes signSGD and other gradient compression schemes","volume-title":"Proc. Int. Conf. Mach. Learn","volume":"97,","author":"Karimireddy","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-274"},{"key":"ref31","first-page":"5325","article-title":"Error compensated quantized SGD and its applications to large-scale distributed optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wu","year":"2018"},{"key":"ref32","first-page":"1","article-title":"Decentralized deep learning with arbitrary communication compression","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Koloskova","year":"2020"},{"key":"ref33","first-page":"6155","article-title":"DoubleSqueeze: Parallel stochastic gradient descent with double-pass error-compensated compression","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tang","year":"2019"},{"key":"ref34","first-page":"19638","article-title":"Analysis of error feedback in federated non-convex optimization with biased compression: Fast convergence and partial participation","volume-title":"Proc. Int. Conf. Mach. Learn","volume":"202","author":"Li","year":"2023"},{"key":"ref35","first-page":"4384","article-title":"EF21: A new, simpler, theoretically better, and practically faster error feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Richtrik","year":"2021"},{"key":"ref36","article-title":"Error feedback reloaded: From quadratic to arithmetic mean of smoothness constants","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Richtrik","year":"2024"},{"key":"ref37","first-page":"76444","article-title":"Momentum provably improves error feedback!","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Fatkhullin","year":"2023"},{"key":"ref38","article-title":"Achieving linear speedup with partial worker participation in non-IID federated learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yang","year":"2021"},{"key":"ref39","first-page":"1","article-title":"Federated optimization: Distributed optimization beyond the datacenter","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Konen","year":"2015"},{"key":"ref40","first-page":"3788","article-title":"MARINA: Faster non-convex distributed learning with compression","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gorbunov","year":"2021"},{"key":"ref41","article-title":"FedPAGE: A fast local stochastic gradient method for communication-efficient federated learning","author":"Zhao","year":"2021"},{"key":"ref42","first-page":"6286","article-title":"PAGE: A simple and optimal probabilistic gradient estimator for nonconvex optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2021"},{"key":"ref43","article-title":"TAMUNA: Accelerated federated learning with local training and partial participation","author":"Condat","year":"2023"},{"key":"ref44","first-page":"906","article-title":"Fedvarp: Tackling the variance due to partial client participation in federated learning","volume-title":"Proc. 38th Conf. Uncertain. Artif. Intell.","author":"Jhunjhunwala","year":"2022"},{"key":"ref45","first-page":"13770","article-title":"Faster rates for compressed federated learning with client-variance reduction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Zhao","year":"2021"},{"key":"ref46","article-title":"EF21 with bells & whistles: Practical algorithmic extensions of modern error feedback","author":"Fatkhullin","year":"2021"},{"key":"ref47","first-page":"18955","article-title":"Lower bounds and nearly optimal algorithms in distributed learning with communication compression","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Huang","year":"2022"},{"key":"ref48","first-page":"31653","article-title":"BEER: Fast $o(1\/t)$ rate for decentralized nonconvex optimization with communication compression","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Zhao","year":"2022"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/0041-5553(64)90137-5"},{"key":"ref50","article-title":"DASHA: Distributed nonconvex optimization with communication compression and optimal oracle complexity","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Tyurin","year":"2023"},{"key":"ref51","article-title":"Variance reduction is an antidote to Byzantines: Better rates, weaker assumptions and communication compression as a cherry on the top","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gorbunov","year":"2023"},{"key":"ref52","first-page":"34900","article-title":"Byzantine robustness and partial participation can be achieved at once: Just clip gradient differences","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Malinovsky","year":"2024"},{"key":"ref53","article-title":"On distributed adaptive optimization with gradient compression","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2022"},{"key":"ref54","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref55","article-title":"On the Convergence of Adam and beyond","author":"Reddi","year":"2018","journal-title":"Proc. Int. Conf. Learn. Representations"},{"key":"ref56","first-page":"17501","article-title":"EF-BV: A unified theory of error feedback and variance reduction mechanisms for biased and unbiased compression in distributed optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Condat","year":"2022"},{"key":"ref57","article-title":"EControl: Fast distributed optimization with compression and error control","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Gao","year":"2023"},{"key":"ref58","article-title":"Accelerated distributed optimization with compression and error feedback","author":"Gao","year":"2025"},{"key":"ref59","first-page":"543","article-title":"A method for solving the convex programming problem with convergence rate $o(1\/k^{2})$","volume":"269","author":"Nesterov","year":"1983","journal-title":"Dokl. Akad. Nauk Sssr"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17246"},{"key":"ref61","article-title":"Clip21: Error feedback for gradient clipping","author":"Khirirat","year":"2023"},{"key":"ref62","article-title":"Double momentum and error feedback for clipping with fast rates and differential privacy","author":"Islamov","year":"2025"},{"key":"ref63","article-title":"Smoothed normalization for efficient distributed private optimization","author":"Shulgin","year":"2025"},{"key":"ref64","first-page":"38018","article-title":"A computation and communication efficient method for distributed nonconvex problems in the partial participation setting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Tyurin","year":"2023"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2022.3168969"},{"key":"ref66","article-title":"Mime: Mimicking centralized stochastic algorithms in federated learning","author":"Karimireddy","year":"2020"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2022.3146399"},{"key":"ref68","article-title":"FEDCCEA: A practical approach of client contribution evaluation for federated learning","author":"Shyn","year":"2021"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2021.3056655"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2025.3583472"},{"key":"ref71","article-title":"Emulating full client participation: A long-term client selection strategy for federated learning","author":"Li","year":"2024"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16920"},{"key":"ref73","article-title":"Spam: Stochastic proximal point method with momentum variance reduction for non-convex cross-device federated learning","author":"Karagulyan","year":"2024"},{"key":"ref74","first-page":"1","article-title":"Momentum benefits non-IID federated learning simply and provably","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Cheng","year":"2024"},{"key":"ref75","first-page":"7184","article-title":"On the linear speedup analysis of communication efficient momentum SGD for distributed non-convex optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yu","year":"2019"},{"key":"ref76","first-page":"6654","article-title":"Quasi-global momentum: Accelerating decentralized deep learning on heterogeneous data","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Lin","year":"2021"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3300886"},{"key":"ref78","article-title":"Error feedback under $(l_{0},l_{1})$-smoothness: Normalization and momentum","author":"Khirirat","year":"2025"},{"key":"ref79","first-page":"10752","article-title":"On convergence of fedprox: Local dissimilarity invariant bounds, non-smoothness and beyond","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Yuan","year":"2022"}],"container-title":["IEEE Transactions on Network Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488902\/11264281\/11316387.pdf?arnumber=11316387","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T20:51:03Z","timestamp":1768596663000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11316387\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":79,"URL":"https:\/\/doi.org\/10.1109\/tnse.2025.3648495","relation":{},"ISSN":["2327-4697","2334-329X"],"issn-type":[{"value":"2327-4697","type":"electronic"},{"value":"2334-329X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}