{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:26:37Z","timestamp":1780637197038,"version":"3.54.1"},"reference-count":81,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"U.S. National Science Foundation","doi-asserted-by":"publisher","award":["IIS-2047570"],"award-info":[{"award-number":["IIS-2047570"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"U.S. National Science Foundation","doi-asserted-by":"publisher","award":["CNS-2044516"],"award-info":[{"award-number":["CNS-2044516"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1109\/tcyb.2023.3247365","type":"journal-article","created":{"date-parts":[[2023,3,8]],"date-time":"2023-03-08T18:29:22Z","timestamp":1678300162000},"page":"401-414","source":"Crossref","is-referenced-by-count":38,"title":["FedLGA: Toward System-Heterogeneity of Federated Learning via Local Gradient Approximation"],"prefix":"10.1109","volume":"54","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5547-9894","authenticated-orcid":false,"given":"Xingyu","family":"Li","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Mississippi State University, Starkville, MS, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2211-2137","authenticated-orcid":false,"given":"Zhe","family":"Qu","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, University of South Florida, Tampa, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5708-766X","authenticated-orcid":false,"given":"Bo","family":"Tang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Worcester Polytechnic Institute, Worcester, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1131-4307","authenticated-orcid":false,"given":"Zhuo","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, University of South Florida, Tampa, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Federated learning: Strategies for improving communication efficiency","author":"Kone\u010dn\u1ef3","year":"2016","journal-title":"arXiv:1610.05492"},{"key":"ref2","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Int. Conf. Artif. Intell. Stat.","author":"McMahan"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2022.3174196"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2013.2247023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3133982"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3164625"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2022.3151234"},{"key":"ref8","article-title":"Local SGD converges fast and communicates little","author":"Stich","year":"2018","journal-title":"arXiv:1805.09767"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015693"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904348"},{"key":"ref11","first-page":"1","article-title":"On the convergence of FedAvg on non-IID data","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"ref13","article-title":"Federated learning with non-IID data","author":"Zhao","year":"2018","journal-title":"arXiv:1806.00582"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2944481"},{"key":"ref15","article-title":"Towards federated learning at scale: System design","author":"Bonawitz","year":"2019","journal-title":"arXiv:1902.01046"},{"key":"ref16","first-page":"4519","article-title":"Tighter theory for local SGD on identical and heterogeneous data","volume-title":"Proc. Int. Conf. Artif. Intell. Stat.","author":"Khaled"},{"key":"ref17","first-page":"5132","article-title":"SCAFFOLD: Stochastic controlled averaging for federated learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Karimireddy"},{"key":"ref18","first-page":"1","article-title":"Achieving linear speedup with partial worker participation in non-IID federated learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yang"},{"key":"ref19","article-title":"Federated learning for mobile keyboard prediction","author":"Hard","year":"2018","journal-title":"arXiv:1811.03604"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.2196\/24207"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-021-01506-3"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2940940"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2937951"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2982168"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3077803"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2021.3126831"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2022.3141734"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3135933"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2022.3233296"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3110369"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3043283"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3090260"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2022.3153964"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3164882"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2022.3165074"},{"key":"ref36","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref37","article-title":"Stragglers are not disaster: A hybrid federated learning algorithm with delayed gradients","author":"Li","year":"2021","journal-title":"arXiv:2102.06329"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-5529-2_5"},{"key":"ref39","article-title":"Federated Meta-learning with fast convergence and efficient communication","author":"Chen","year":"2018","journal-title":"arXiv:1802.07876"},{"key":"ref40","first-page":"5917","article-title":"Adaptive gradient-based Meta-learning methods","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Khodak"},{"key":"ref41","first-page":"4424","article-title":"Federated multi-task learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Smith"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/tpds.2022.3186960"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3065340"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2022.3140338"},{"key":"ref45","article-title":"Adaptive federated optimization","author":"Reddi","year":"2020","journal-title":"arXiv:2003.00295"},{"key":"ref46","article-title":"Federated learning based on dynamic regularization","author":"Acar","year":"2021","journal-title":"arXiv:2111.04263"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1561\/2200000083"},{"key":"ref48","first-page":"1","article-title":"Tackling the objective inconsistency problem in heterogeneous federated optimization","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Wang"},{"key":"ref49","article-title":"The error-feedback framework: Better rates for SGD with delayed gradients and compressed communication","author":"Stich","year":"2019","journal-title":"arXiv:1909.05350"},{"key":"ref50","first-page":"111","article-title":"A tight convergence analysis for stochastic gradient descent with delayed updates","volume-title":"Proc. Int. Conf. Algorithmic Learn. Theory","author":"Arjevani"},{"key":"ref51","article-title":"Asynchronous distributed optimization with stochastic delays","author":"Glasgow","year":"2020","journal-title":"arXiv:2009.10717"},{"key":"ref52","first-page":"4387","article-title":"The non-IID data quagmire of decentralized machine learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hsieh"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1080\/00029890.1990.11995583"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1080\/10556789308805543"},{"key":"ref55","first-page":"4120","article-title":"Asynchronous stochastic gradient descent with delay compensation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zheng"},{"key":"ref56","article-title":"Asynchronous federated optimization","author":"Xie","year":"2019","journal-title":"arXiv:1903.03934"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7"},{"key":"ref58","article-title":"Revisiting natural gradient for deep networks","author":"Pascanu","year":"2013","journal-title":"arXiv:1301.3584"},{"key":"ref59","first-page":"192","article-title":"The loss surfaces of multilayer networks","volume-title":"Proc. Int. Conf. Artif. Intell. Stat.","author":"Choromanska"},{"key":"ref60","first-page":"586","article-title":"Deep learning without poor local minima","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Kawaguchi"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2023.100595"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA51294.2020.00185"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.dcan.2021.04.001"},{"key":"ref64","article-title":"FedAT: A high-performance and communication-efficient federated learning system with asynchronous tiers","author":"Chai","year":"2020","journal-title":"arXiv:2010.05958"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1137\/120880811"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1137\/16M1080173"},{"key":"ref67","article-title":"FedLGA: Towards system-heterogeneity of federated learning via local gradient approximation","author":"Li","year":"2021","journal-title":"arXiv:2112.11989"},{"key":"ref68","article-title":"First analysis of local GD on heterogeneous data","author":"Khaled","year":"2019","journal-title":"arXiv:1909.04715"},{"key":"ref69","article-title":"Generalized federated learning via sharpness aware minimization","author":"Qu","year":"2022","journal-title":"arXiv:2206.02618"},{"key":"ref70","first-page":"3581","article-title":"Federated learning with buffered asynchronous aggregation","volume-title":"Proc. Int. Conf. Artif. Intell. Stat.","author":"Nguyen"},{"key":"ref71","first-page":"1","article-title":"Automatic differentiation in PyTorch","volume-title":"Proc. NIPS-W","author":"Paszke"},{"key":"ref72","article-title":"Think locally, act globally: Federated learning with local and global representations","author":"Liang","year":"2020","journal-title":"arXiv:2001.01523"},{"key":"ref73","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017","journal-title":"arXiv:1708.07747"},{"key":"ref74","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref75","first-page":"315","article-title":"Accelerating stochastic gradient descent using predictive variance reduction","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"26","author":"Johnson"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-016-1030-6"},{"key":"ref77","article-title":"FedCM: Federated learning with client-level momentum","author":"Xu","year":"2021","journal-title":"arXiv:2106.10874"},{"key":"ref78","article-title":"Mime: Mimicking centralized stochastic algorithms in federated learning","author":"Karimireddy","year":"2020","journal-title":"arXiv:2008.03606"},{"key":"ref79","first-page":"1","article-title":"Sharpness-aware minimization for efficiently improving generalization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Foret"},{"key":"ref80","first-page":"1","article-title":"Deep gradient compression: Reducing the communication bandwidth for distributed training","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lin"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5793"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6221036\/10367425\/10063977-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/10367425\/10063977.pdf?arnumber=10063977","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T18:55:09Z","timestamp":1732906509000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10063977\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":81,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2023.3247365","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1]]}}}