{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T20:08:42Z","timestamp":1784750922992,"version":"3.55.0"},"reference-count":45,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["22DZ2229014"],"award-info":[{"award-number":["22DZ2229014"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007219","name":"Shanghai Municipal Natural Science Foundation","doi-asserted-by":"publisher","award":["22ZR1419500"],"award-info":[{"award-number":["22ZR1419500"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.neucom.2026.134475","type":"journal-article","created":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T15:19:56Z","timestamp":1784042396000},"page":"134475","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["FedAPEX: Find flatter minima via federated accelerated perturbation exploration"],"prefix":"10.1016","volume":"701","author":[{"given":"Yuan","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9870-2893","authenticated-orcid":false,"given":"Xuesong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8377-0163","authenticated-orcid":false,"given":"Liyan","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6804-2651","authenticated-orcid":false,"given":"Fang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.134475_bib0005","doi-asserted-by":"crossref","first-page":"406","DOI":"10.1016\/j.future.2021.10.016","article-title":"Communication-efficient hierarchical federated learning for IoT heterogeneous systems with imbalanced data","volume":"128","author":"Abdellatif","year":"2022","journal-title":"Future Gener. Comput. Syst."},{"key":"10.1016\/j.neucom.2026.134475_bib0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2021.104468","article-title":"Achieving security and privacy in federated learning systems: survey, research challenges and future directions","volume":"106","author":"Blanco-Justicia","year":"2021","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.neucom.2026.134475_bib0015","series-title":"European Conference on Computer Vision","first-page":"654","article-title":"Improving generalization in federated learning by seeking flat minima","author":"Caldarola","year":"2022"},{"key":"10.1016\/j.neucom.2026.134475_bib0020","series-title":"Proceedings of the National Academy of Sciences 118","article-title":"Communication-efficient federated learning","author":"Chen","year":"2021"},{"key":"10.1016\/j.neucom.2026.134475_bib0025","series-title":"International Joint Conference on Neural Networks","first-page":"2921","article-title":"EMNIST: extending MNIST to handwritten letters","author":"Cohen","year":"2017"},{"issue":"12","key":"10.1016\/j.neucom.2026.134475_bib0030","doi-asserted-by":"crossref","first-page":"17479","DOI":"10.1109\/TNNLS.2023.3304453","article-title":"FedGAMMA: federated learning with global sharpness-aware minimization","volume":"35","author":"Dai","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.neucom.2026.134475_bib0035","doi-asserted-by":"crossref","DOI":"10.1016\/j.automatica.2023.111460","article-title":"Shed: a Newton-type algorithm for federated learning based on incremental Hessian eigenvector sharing","volume":"160","author":"Dal Fabbro","year":"2024","journal-title":"Automatica"},{"key":"10.1016\/j.neucom.2026.134475_bib0040","series-title":"International Conference on Learning Representations","article-title":"Federated learning based on dynamic regularization","author":"Durmus","year":"2021"},{"key":"10.1016\/j.neucom.2026.134475_bib0045","series-title":"International Conference on Machine Learning","first-page":"12858","article-title":"Locally estimated global perturbations are better than local perturbations for federated sharpness-aware minimization","author":"Fan","year":"2024"},{"key":"10.1016\/j.neucom.2026.134475_bib0050","series-title":"International Conference on Learning Representations","article-title":"Sharpness-aware minimization for efficiently improving generalization","author":"Foret","year":"2021"},{"key":"10.1016\/j.neucom.2026.134475_bib0055","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10112","article-title":"Feddc: federated learning with non-iid data via local drift decoupling and correction","author":"Gao","year":"2022"},{"key":"10.1016\/j.neucom.2026.134475_bib0060","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110424","article-title":"Federated learning for medical image analysis: a survey","volume":"151","author":"Guan","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.neucom.2026.134475_bib0065","series-title":"International Conference on Learning Representations","article-title":"Stochastic weight averaging in parallel: large-batch training that generalizes well","author":"Gupta","year":"2020"},{"key":"10.1016\/j.neucom.2026.134475_bib0070","first-page":"1050","article-title":"Averaging weights leads to wider optima and better generalization","volume":"55","author":"Izmailov","year":"2022","journal-title":"Find. Assoc. Comput. Linguist.: EMNLP 2022"},{"key":"10.1016\/j.neucom.2026.134475_bib0075","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113967","article-title":"Sharpness-aware minimization method with momentum acceleration for deep neural networks","volume":"326","author":"Kang","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.neucom.2026.134475_bib0080","first-page":"28663","article-title":"Breaking the centralized barrier for cross-device federated learning","volume":"34","author":"Karimireddy","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134475_bib0085","series-title":"International Conference on Machine Learning","first-page":"5132","article-title":"SCAFFOLD: stochastic controlled averaging for federated learning","author":"Karimireddy","year":"2020"},{"key":"10.1016\/j.neucom.2026.134475_bib0090","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12385","article-title":"Communication-efficient federated learning with accelerated client gradient","author":"Kim","year":"2024"},{"key":"10.1016\/j.neucom.2026.134475_bib0095","series-title":"Learning Multiple Layers of Features From Tiny Images","author":"Krizhevsky","year":"2009"},{"key":"10.1016\/j.neucom.2026.134475_bib0100","first-page":"6391","article-title":"Visualizing the loss landscape of neural nets","volume":"31","author":"Li","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134475_bib0105","series-title":"Proceedings of Machine Learning and Systems","first-page":"429","article-title":"Federated optimization in heterogeneous networks","author":"Li","year":"2020"},{"key":"10.1016\/j.neucom.2026.134475_bib0110","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"4224","article-title":"Fedrec++: lossless federated recommendation with explicit feedback","author":"Liang","year":"2021"},{"key":"10.1016\/j.neucom.2026.134475_bib0115","series-title":"Proceedings of the ACM SIGIR Conference on Research and Development in Information Retrieval","first-page":"716","article-title":"FedCT: federated collaborative transfer for recommendation","author":"Liu","year":"2021"},{"key":"10.1016\/j.neucom.2026.134475_bib0120","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128653","article-title":"Federated learning data protection scheme based on personalized differential privacy in psychological evaluation","volume":"611","author":"Liu","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134475_bib0125","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"McMahan","year":"2017","journal-title":"Artif. Intell. Stat."},{"key":"10.1016\/j.neucom.2026.134475_bib0130","first-page":"14606","article-title":"Linear convergence in federated learning: tackling client heterogeneity and sparse gradients","volume":"34","author":"Mitra","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134475_bib0135","series-title":"Lectures on Convex Optimization","volume":"vol. 137","author":"Nesterov","year":"2018"},{"key":"10.1016\/j.neucom.2026.134475_bib0140","first-page":"543","article-title":"A method for solving the convex programming problem with convergence rate o(1\/k2","volume":"269","author":"Nesterov","year":"1983","journal-title":"Dokl. Akad. Nauk"},{"key":"10.1016\/j.neucom.2026.134475_bib0145","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/0041-5553(64)90137-5","article-title":"Some methods of speeding up the convergence of iteration methods","volume":"4","author":"Polyak","year":"1964","journal-title":"USSR Comput. Math. Math. Phys."},{"key":"10.1016\/j.neucom.2026.134475_bib0150","series-title":"International Conference on Machine Learning","first-page":"18250","article-title":"Generalized federated learning via sharpness aware minimization","author":"Qu","year":"2022"},{"key":"10.1016\/j.neucom.2026.134475_bib0155","doi-asserted-by":"crossref","first-page":"1143","DOI":"10.1613\/jair.1.15180","article-title":"A unified linear speedup analysis of federated averaging and nesterov FedAvg","volume":"78","author":"Qu","year":"2023","journal-title":"J. Artif. Intell. Res."},{"key":"10.1016\/j.neucom.2026.134475_bib0160","author":"Rahil"},{"key":"10.1016\/j.neucom.2026.134475_bib0165","series-title":"International Conference on Learning Representations","article-title":"Adaptive federated optimization","author":"Reddi","year":"2021"},{"key":"10.1016\/j.neucom.2026.134475_bib0170","series-title":"International Conference on Machine Learning","first-page":"32991","article-title":"Dynamic regularized sharpness aware minimization in federated learning: approaching global consistency and smooth landscape","author":"Sun","year":"2023"},{"key":"10.1016\/j.neucom.2026.134475_bib0175","doi-asserted-by":"crossref","first-page":"14453","DOI":"10.1109\/TPAMI.2023.3300886","article-title":"Efficient federated learning via local adaptive amended optimizer with linear speedup","volume":"45","author":"Sun","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134475_bib0180","doi-asserted-by":"crossref","first-page":"749","DOI":"10.1038\/s42256-021-00390-3","article-title":"Adversarial interference and its mitigations in privacy-preserving collaborative machine learning","volume":"3","author":"Usynin","year":"2021","journal-title":"Nat. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134475_bib0185","series-title":"International Conference on Learning Representations","article-title":"SlowMo: improving communication-efficient distributed SGD with slow momentum","author":"Wang","year":"2020"},{"key":"10.1016\/j.neucom.2026.134475_bib0190","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"21707","article-title":"Flexible sharpness-aware personalized federated learning","author":"Xing","year":"2025"},{"key":"10.1016\/j.neucom.2026.134475_bib0195","doi-asserted-by":"crossref","first-page":"1932","DOI":"10.1109\/TMI.2022.3233574","article-title":"Label-efficient self-supervised federated learning for tackling data heterogeneity in medical imaging","volume":"42","author":"Yan","year":"2023","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.neucom.2026.134475_bib0200","series-title":"International Conference on Learning Representations","article-title":"Achieving linear speedup with partial worker participation in non-IID federated learning","author":"Yang","year":"2021"},{"key":"10.1016\/j.neucom.2026.134475_bib0205","series-title":"International Conference on Machine Learning","first-page":"7184","article-title":"On the linear speedup analysis of communication efficient momentum SGD for distributed non-convex optimization","author":"Yu","year":"2019"},{"key":"10.1016\/j.neucom.2026.134475_bib0210","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1109\/TPAMI.2024.3469188","article-title":"Stabilizing and accelerating federated learning on heterogeneous data with partial client participation","volume":"47","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134475_bib0215","article-title":"A two-stage personalized Federal learning approach based on a hybrid expert architecture","author":"Zhang","year":"2026","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134475_bib0220","author":"Zhang"},{"key":"10.1016\/j.neucom.2026.134475_bib0225","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1109\/TPAMI.2024.3470072","article-title":"Medical federated model with mixture of personalized and shared components","volume":"47","author":"Zhao","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226018734?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226018734?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T19:22:07Z","timestamp":1784748127000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226018734"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":45,"alternative-id":["S0925231226018734"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134475","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"FedAPEX: Find flatter minima via federated accelerated perturbation exploration","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134475","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"134475"}}