{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T05:56:57Z","timestamp":1777874217552,"version":"3.51.4"},"reference-count":51,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012456","name":"National Social Science Fund of China","doi-asserted-by":"publisher","award":["23VRC094"],"award-info":[{"award-number":["23VRC094"]}],"id":[{"id":"10.13039\/501100012456","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012456","name":"National Social Science Fund of China","doi-asserted-by":"publisher","award":["22&ZD147"],"award-info":[{"award-number":["22&ZD147"]}],"id":[{"id":"10.13039\/501100012456","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004773","name":"Henan University","doi-asserted-by":"publisher","award":["24IRTSTHN021"],"award-info":[{"award-number":["24IRTSTHN021"]}],"id":[{"id":"10.13039\/501100004773","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.neucom.2026.133648","type":"journal-article","created":{"date-parts":[[2026,4,12]],"date-time":"2026-04-12T16:31:09Z","timestamp":1776011469000},"page":"133648","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["A two-stage personalized federal learning approach based on a hybrid expert architecture"],"prefix":"10.1016","volume":"685","author":[{"given":"Lei","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Junhao","family":"Niu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3855-0994","authenticated-orcid":false,"given":"Wenbo","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Feng","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Jiang","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.133648_bib0005","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"McMahan","year":"2017","journal-title":"AISTATS"},{"key":"10.1016\/j.neucom.2026.133648_bib0010","series-title":"Proceedings of Machine Learning and Systems","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume":"vol. 2","author":"Li","year":"2020"},{"key":"10.1016\/j.neucom.2026.133648_bib0015","series-title":"International Conference on Machine Learning","first-page":"5132","article-title":"Stochastic controlled averaging for federated learning","author":"Karimireddy","year":"2020"},{"key":"10.1016\/j.neucom.2026.133648_bib0020","series-title":"International Conference on Machine Learning","first-page":"12878","article-title":"Data-free knowledge distillation for heterogeneous federated learning","author":"Zhu","year":"2021"},{"key":"10.1016\/j.neucom.2026.133648_bib0025","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10713","article-title":"Model-contrastive federated learning","author":"Li","year":"2021"},{"key":"10.1016\/j.neucom.2026.133648_bib0030","author":"Arivazhagan"},{"key":"10.1016\/j.neucom.2026.133648_bib0035","author":"Zhang"},{"key":"10.1016\/j.neucom.2026.133648_bib0040","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"7865","article-title":"Personalized cross-silo federated learning on non-iid data","volume":"vol. 35","author":"Huang","year":"2021"},{"key":"10.1016\/j.neucom.2026.133648_bib0045","author":"Li"},{"key":"10.1016\/j.neucom.2026.133648_bib0050","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"8432","article-title":"Federated prototype learning across heterogeneous clients","volume":"vol. 36","author":"Tan","year":"2022"},{"key":"10.1016\/j.neucom.2026.133648_bib0055","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"19375","article-title":"BOLD but cautious: unlocking the potential of personalized federated learning through cautiously aggressive collaboration","author":"Wu","year":"2023"},{"key":"10.1016\/j.neucom.2026.133648_bib0060","series-title":"NeurIPS.","article-title":"Eliminating domain bias for federated learning in representation space","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neucom.2026.133648_bib0065","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1080\/00401706.2022.2157882","article-title":"Personalized federated learning via domain adaptation with an application to distributed 3d printing","volume":"65","author":"Shi","year":"2023","journal-title":"Technometrics."},{"key":"10.1016\/j.neucom.2026.133648_bib0070","series-title":"International Conference on Machine Learning","first-page":"2089","article-title":"Exploiting shared representations for personalized federated learning","author":"Collins","year":"2021"},{"key":"10.1016\/j.neucom.2026.133648_bib0075","author":"Chen"},{"key":"10.1016\/j.neucom.2026.133648_bib0080","author":"Oh"},{"key":"10.1016\/j.neucom.2026.133648_bib0085","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"5041","article-title":"Gpfl: simultaneously learning global and personalized feature information for personalized federated learning","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neucom.2026.133648_bib0090","series-title":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","first-page":"3249","article-title":"Fedcp: separating feature information for personalized federated learning via conditional policy","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neucom.2026.133648_bib0095","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11986","article-title":"Fedas: bridging inconsistency in personalized federated learning","author":"Yang","year":"2024"},{"key":"10.1016\/j.neucom.2026.133648_bib0100","series-title":"Personalized Federated Learning with Multiple Classifier Aggregation","author":"Zheng","year":"2025"},{"key":"10.1016\/j.neucom.2026.133648_bib0105","series-title":"2022 IEEE 38th International Conference on Data Engineering (ICDE)","first-page":"965","article-title":"Federated learning on non-iid data silos: an experimental study","author":"Li","year":"2022"},{"key":"10.1016\/j.neucom.2026.133648_bib0110","doi-asserted-by":"crossref","first-page":"2840","DOI":"10.1109\/TIFS.2024.3356233","article-title":"Securereid: privacy-preserving anonymization for person re-identification","volume":"19","author":"Ye","year":"2024","journal-title":"IEEE Transactions On Information Forensics And Security."},{"key":"10.1016\/j.neucom.2026.133648_bib0115","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1007\/s13042-022-01647-y","article-title":"A survey on federated learning: challenges and applications","volume":"14","author":"Wen","year":"2023","journal-title":"International Journal Of Machine Learning And Cybernetics."},{"key":"10.1016\/j.neucom.2026.133648_bib0120","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1038\/s41746-020-00323-1","article-title":"& others the future of digital health with federated learning","volume":"3","author":"Rieke","year":"2020","journal-title":"NPJ Digital Medicine."},{"key":"10.1016\/j.neucom.2026.133648_bib0125","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1038\/s41591-021-01506-3","article-title":"& others federated learning for predicting clinical outcomes in patients with COVID-19","volume":"27","author":"Dayan","year":"2021","journal-title":"Nature Medicine."},{"key":"10.1016\/j.neucom.2026.133648_bib0130","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3453476","article-title":"Federated learning for smart healthcare: a survey","volume":"55","author":"Nguyen","year":"2022","journal-title":"ACM Computing Surveys (Csur)."},{"key":"10.1016\/j.neucom.2026.133648_bib0135","doi-asserted-by":"crossref","first-page":"2508","DOI":"10.1109\/TCE.2023.3339702","article-title":"Federated learning empowered recommendation model for financial consumer services","volume":"70","author":"Chatterjee","year":"2023","journal-title":"IEEE Transactions On Consumer Electronics."},{"key":"10.1016\/j.neucom.2026.133648_bib0140","article-title":"16 federated knowledge distillation","volume":"457","author":"Seo","year":"2022","journal-title":"Machine Learning And Wireless Communications."},{"key":"10.1016\/j.neucom.2026.133648_bib0145","doi-asserted-by":"crossref","first-page":"2032","DOI":"10.1038\/s41467-022-29763-x","article-title":"Communication-efficient federated learning via knowledge distillation","volume":"13","author":"Wu","year":"2022","journal-title":"Nature Communications."},{"key":"10.1016\/j.neucom.2026.133648_bib0150","author":"Xu"},{"key":"10.1016\/j.neucom.2026.133648_bib0155","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1007\/s10462-012-9338-y","article-title":"Mixture of experts: a literature survey","volume":"42","author":"Masoudnia","year":"2014","journal-title":"Artificial Intelligence Review."},{"key":"10.1016\/j.neucom.2026.133648_bib0160","doi-asserted-by":"crossref","first-page":"1177","DOI":"10.1109\/TNNLS.2012.2200299","article-title":"Twenty years of mixture of experts","volume":"23","author":"Yuksel","year":"2012","journal-title":"IEEE Transactions On Neural Networks And Learning Systems."},{"key":"10.1016\/j.neucom.2026.133648_bib0165","series-title":"Hierarchical Mixtures-of-Experts for Exponential Family Regression Models: Approximation and Maximum Likelihood Estimation","first-page":"987","author":"Jiang","year":"1999"},{"key":"10.1016\/j.neucom.2026.133648_bib0170","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"2002","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.neucom.2026.133648_bib0175","author":"Xiao"},{"key":"10.1016\/j.neucom.2026.133648_bib0180","series-title":"Learning Multiple Layers of Features from Tiny Images","author":"Krizhevsky","year":"2009"},{"key":"10.1016\/j.neucom.2026.133648_bib0185","first-page":"1","article-title":"PFLlib: a Beginner-Friendly and comprehensive personalized federated learning library and benchmark","volume":"26","author":"Zhang","year":"2025","journal-title":"Journal Of Machine Learning Research."},{"key":"10.1016\/j.neucom.2026.133648_bib0190","series-title":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","article-title":"HtFLlib: a comprehensive heterogeneous federated learning library and benchmark","author":"Zhang","year":"2025"},{"key":"10.1016\/j.neucom.2026.133648_bib0195","author":"Hsu"},{"key":"10.1016\/j.neucom.2026.133648_bib0200","series-title":"ICC 2020-2020 IEEE International Conference on Communications (ICC)","first-page":"1","article-title":"Client-edge-cloud hierarchical federated learning","author":"Liu","year":"2020"},{"key":"10.1016\/j.neucom.2026.133648_bib0205","first-page":"1","article-title":"Heterogeneous federated learning: state-of-the-art and research challenges","volume":"56","author":"Ye","year":"2023","journal-title":"ACM Computing Surveys."},{"key":"10.1016\/j.neucom.2026.133648_bib0210","author":"Jiang"},{"key":"10.1016\/j.neucom.2026.133648_bib0215","author":"Acar"},{"key":"10.1016\/j.neucom.2026.133648_bib0220","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2022.103061","article-title":"Federated learning review: fundamentals, enabling technologies, and future applications","volume":"59","author":"Banabilah","year":"2022","journal-title":"Information Processing & Management."},{"key":"10.1016\/j.neucom.2026.133648_bib0225","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1016\/j.future.2022.05.003","article-title":"A state-of-the-art survey on solving non-iid data in federated learning","volume":"135","author":"Ma","year":"2022","journal-title":"Future Generation Computer Systems."},{"key":"10.1016\/j.neucom.2026.133648_bib0230","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1186\/s13677-022-00377-4","article-title":"Federated learning in cloud-edge collaborative architecture: key technologies, applications and challenges","volume":"11","author":"Bao","year":"2022","journal-title":"Journal Of Cloud Computing."},{"key":"10.1016\/j.neucom.2026.133648_bib0235","doi-asserted-by":"crossref","DOI":"10.1016\/j.cie.2020.106854","article-title":"A review of applications in federated learning","volume":"149","author":"Li","year":"2020","journal-title":"Computers & Industrial Engineering."},{"key":"10.1016\/j.neucom.2026.133648_bib0240","unstructured":"Y. Le, X. Yang, Tiny imagenet visual recognition challenge, CS 231N. 7 (7) (2015) 3."},{"key":"10.1016\/j.neucom.2026.133648_bib0245","series-title":"Proceedings of the ACM on Web Conference 2025","first-page":"134","article-title":"Mixture of experts on private model parameters for personalized federated learning","author":"Feng","year":"2025"},{"key":"10.1016\/j.neucom.2026.133648_bib0250","author":"Yi"},{"key":"10.1016\/j.neucom.2026.133648_bib0255","author":"Zhan"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226010453?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226010453?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T19:19:53Z","timestamp":1777576793000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226010453"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":51,"alternative-id":["S0925231226010453"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133648","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A two-stage personalized federal learning approach based on a hybrid expert architecture","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133648","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":"133648"}}