{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T22:22:37Z","timestamp":1784067757069,"version":"3.55.0"},"reference-count":82,"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":[{"name":"Major Science and Technology Projects of Longmen Laboratory","award":["231100220300"],"award-info":[{"award-number":["231100220300"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372416"],"award-info":[{"award-number":["62372416"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006407","name":"Natural Science Foundation of Henan Province","doi-asserted-by":"publisher","award":["242300421215"],"award-info":[{"award-number":["242300421215"]}],"id":[{"id":"10.13039\/501100006407","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation","award":["2025-BS-0212"],"award-info":[{"award-number":["2025-BS-0212"]}]},{"DOI":"10.13039\/501100017683","name":"Dalian Science and Technology Innovation Fund","doi-asserted-by":"publisher","award":["2024JB11GX001"],"award-info":[{"award-number":["2024JB11GX001"]}],"id":[{"id":"10.13039\/501100017683","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.2025.3638762","type":"journal-article","created":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T18:25:25Z","timestamp":1764613525000},"page":"5000-5017","source":"Crossref","is-referenced-by-count":3,"title":["Neighborhood and Global Perturbations Supported Sharpness-Aware Minimization in Federated Learning: From Local Tweaks to Global Awareness"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9306-9303","authenticated-orcid":false,"given":"Boyuan","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science and Artificial Intelligence, Zhengzhou University, Zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3108-123X","authenticated-orcid":false,"given":"Zihao","family":"Peng","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing Normal University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9651-6092","authenticated-orcid":false,"given":"Yafei","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Artificial Intelligence, Zhengzhou University, Zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3901-6790","authenticated-orcid":false,"given":"Zijian","family":"Li","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence, Dalian Maritime University, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9026-8128","authenticated-orcid":false,"given":"Shengbo","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Software, Nanchang University, Nanchang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3148-4453","authenticated-orcid":false,"given":"Cong","family":"Shen","sequence":"additional","affiliation":[{"name":"University of Virginia, Charlottesville, VA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4037-3149","authenticated-orcid":false,"given":"Tony Q.S.","family":"Quek","sequence":"additional","affiliation":[{"name":"Singapore University of Technology and Design, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","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":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM54844.2022.00023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.5772\/intechopen.1008364"},{"key":"ref4","first-page":"10334","article-title":"Is local SGD better than minibatch SGD?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Woodworth","year":"2020"},{"key":"ref5","article-title":"speedtest.net","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3115952"},{"key":"ref7","first-page":"7611","article-title":"Tackling the objective inconsistency problem in heterogeneous federated optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2020"},{"key":"ref8","first-page":"13431","article-title":"On the convergence of FedAvg on non-IID data","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2020"},{"key":"ref9","first-page":"1","article-title":"Visualizing the loss landscape of neural nets","author":"Li","year":"2018"},{"key":"ref10","first-page":"18250","article-title":"Generalized federated learning via sharpness aware minimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qu","year":"2022"},{"key":"ref11","first-page":"8889","article-title":"FedSpeed: Larger local interval, less communication round, and higher generalization accuracy","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sun","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3304453"},{"key":"ref13","first-page":"32991","article-title":"Dynamic regularized sharpness aware minimization in federated learning: Approaching global consistency and smooth landscape","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sun","year":"2023"},{"key":"ref14","first-page":"12858","article-title":"Locally estimated global perturbations are better than local perturbations for federated sharpness-aware minimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fan","year":"2024"},{"key":"ref15","first-page":"6692","article-title":"From local SGD to local fixed-point methods for federated learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Malinovskiy","year":"2020"},{"key":"ref16","first-page":"3514","article-title":"Sharpness-aware minimization for efficiently improving generalization","author":"Foret","year":"2019","journal-title":"Int. Conf. Learn. Representations"},{"key":"ref17","first-page":"790","article-title":"Federated learning based on dynamic regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Acar","year":"2021"},{"key":"ref18","article-title":"Local SGD converges fast and communicates little","author":"Stich","year":"2018"},{"key":"ref19","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume-title":"Proc. Mach. Learn. Syst.","volume":"2","author":"Li","year":"2020"},{"key":"ref20","first-page":"5132","article-title":"SCAFFOLD: Stochastic controlled averaging for federated learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Karimireddy","year":"2020"},{"key":"ref21","first-page":"28663","article-title":"Breaking the centralized barrier for cross-device federated learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Karimireddy","year":"2021"},{"key":"ref22","first-page":"10790","article-title":"Federated learning via posterior averaging: A new perspective and practical algorithms","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Al-Shedivat","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00987"},{"key":"ref24","first-page":"38461","article-title":"Preservation of the global knowledge by not-true distillation in federated learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lee","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01189"},{"key":"ref26","article-title":"Overcoming forgetting in federated learning on non-IID data","author":"Shoham","year":"2019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3498346"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3327373"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00992"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i13.29439"},{"key":"ref32","first-page":"9815","article-title":"Adaptive methods for nonconvex optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zaheer","year":"2018"},{"key":"ref33","article-title":"Adaptive federated optimization","author":"Reddi","year":"2020"},{"key":"ref34","first-page":"7408","article-title":"Adaptive federated optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Reddi","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(98)00116-6"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01177"},{"issue":"3","key":"ref37","article-title":"A method for unconstrained convex minimization problem with the rate of convergence O(1\/k2)","volume":"269","author":"Nesterov","year":"1983","journal-title":"Dokl. Akad. Nauk. SSSR"},{"key":"ref38","first-page":"31955","article-title":"FedExP: Speeding up federated averaging via extrapolation","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Jhunjhunwala","year":"2023"},{"key":"ref39","article-title":"FEDCM: Federated learning with client-level momentum","author":"Xu","year":"2021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3300886"},{"key":"ref41","article-title":"Personalized federated learning: A meta-learning approach","author":"Fallah","year":"2020"},{"key":"ref42","first-page":"21394","article-title":"Personalized federated learning with Moreau envelopes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dinh","year":"2020"},{"key":"ref43","first-page":"2089","article-title":"Exploiting shared representations for personalized federated learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Collins","year":"2021"},{"key":"ref44","first-page":"6357","article-title":"Ditto: Fair and robust federated learning through personalization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16960"},{"key":"ref46","first-page":"9489","article-title":"Personalized federated learning using hypernetworks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Shamsian","year":"2021"},{"key":"ref47","first-page":"19332","article-title":"Federated learning from pre-trained models: A contrastive learning approach","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tan","year":"2022"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26330"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/tit.2022.3192506"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3015958"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20785"},{"key":"ref52","article-title":"FedGroup: Efficient clustered federated learning via decomposed data-driven measure","author":"Duan","year":"2020"},{"key":"ref53","first-page":"12432","article-title":"Federated learning with matched averaging","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2020"},{"key":"ref54","first-page":"2351","article-title":"Ensemble distillation for robust model fusion in federated learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lin","year":"2020"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.31577\/cai_2024_1_1"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583305"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01057"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00168"},{"key":"ref59","article-title":"FedMD: Heterogenous federated learning via model distillation","author":"Li","year":"2019"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2023.3315066"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00993"},{"key":"ref62","article-title":"FedCLIP: Fast generalization and personalization for CLIP in federated learning","volume-title":"ICLR Workshop Trustworthy Reliable Large-Scale Mach. Learn. Models","author":"Lu","year":"2023"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095356"},{"key":"ref64","article-title":"FedDistill: Global model distillation for local model de-biasing in non-IID federated learning","author":"Song","year":"2024"},{"key":"ref65","article-title":"Asynchronous federated optimization","author":"Xie","year":"2019"},{"key":"ref66","first-page":"3581","article-title":"Federated learning with buffered asynchronous aggregation","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Nguyen","year":"2022"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3118435"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3176469"},{"key":"ref69","first-page":"529","article-title":"Simplifying neural nets by discovering flat minima","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hochreiter","year":"1994"},{"key":"ref70","first-page":"1019","article-title":"Sharp minima can generalize for deep nets","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dinh","year":"2017"},{"key":"ref71","first-page":"2874","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Keskar","year":"2017"},{"key":"ref72","article-title":"Momentum-SAM: Sharpness aware minimization without computational overhead","author":"Becker","year":"2024"},{"key":"ref73","first-page":"70861","article-title":"Enhancing sharpness-aware optimization through variance suppression","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2023"},{"key":"ref74","first-page":"69228","article-title":"Normalization layers are all that sharpness-aware minimization needs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mueller","year":"2023"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20050-2_38"},{"key":"ref76","first-page":"15241","article-title":"Federated domain generalization with data-free on-server gradient matching","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Nguyen","year":"2025"},{"key":"ref77","first-page":"35317","article-title":"One arrow, two hawks: Sharpness-aware minimization for federated learning via global model trajectory","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2025"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CDC51059.2022.9992745"},{"key":"ref79","first-page":"9597","article-title":"Lookahead optimizer: K steps forward, 1 step back","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang","year":"2019"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01167"},{"key":"ref81","first-page":"80543","article-title":"Understanding how consistency works in federated learning via stage-wise relaxed initialization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sun","year":"2024"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["IEEE Transactions on Network Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488902\/11264281\/11271547.pdf?arnumber=11271547","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:02:41Z","timestamp":1768255361000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11271547\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":82,"URL":"https:\/\/doi.org\/10.1109\/tnse.2025.3638762","relation":{},"ISSN":["2327-4697","2334-329X"],"issn-type":[{"value":"2327-4697","type":"electronic"},{"value":"2334-329X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}