{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T07:15:01Z","timestamp":1783149301727,"version":"3.54.6"},"reference-count":35,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100004479","name":"Natural Science Foundation of Jiangxi Province","doi-asserted-by":"publisher","award":["20252BAC250012"],"award-info":[{"award-number":["20252BAC250012"]}],"id":[{"id":"10.13039\/501100004479","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004479","name":"Natural Science Foundation of Jiangxi Province","doi-asserted-by":"publisher","award":["20252BAC250063"],"award-info":[{"award-number":["20252BAC250063"]}],"id":[{"id":"10.13039\/501100004479","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012659","name":"Foundation for Innovative Research Groups of the National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62566023"],"award-info":[{"award-number":["62566023"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62366015"],"award-info":[{"award-number":["62366015"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Communications"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1016\/j.comcom.2026.108552","type":"journal-article","created":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T15:49:47Z","timestamp":1777564187000},"page":"108552","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Personalized federated learning with two-stage adaptive aggregation under global feature constraints"],"prefix":"10.1016","volume":"254","author":[{"given":"Huan","family":"Zhong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9735-3974","authenticated-orcid":false,"given":"Lu","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanyuan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.comcom.2026.108552_b1","series-title":"Artificial Intelligence and Statistics","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"McMahan","year":"2017"},{"key":"10.1016\/j.comcom.2026.108552_b2","series-title":"Federated learning with non-iid data","author":"Zhao","year":"2018"},{"key":"10.1016\/j.comcom.2026.108552_b3","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1016\/j.neucom.2021.07.098","article-title":"Federated learning on non-IID data: A survey","volume":"465","author":"Zhu","year":"2021","journal-title":"Neurocomputing"},{"key":"10.1016\/j.comcom.2026.108552_b4","series-title":"2022 IEEE 38th International Conference on Data Engineering","first-page":"965","article-title":"Federated learning on non-iid data silos: An experimental study","author":"Li","year":"2022"},{"key":"10.1016\/j.comcom.2026.108552_b5","doi-asserted-by":"crossref","unstructured":"Bingyan Liu, Yao Guo, Xiangqun Chen, PFA: Privacy-preserving federated adaptation for effective model personalization, in: Proceedings of the Web Conference 2021, 2021, pp. 923\u2013934.","DOI":"10.1145\/3442381.3449847"},{"key":"10.1016\/j.comcom.2026.108552_b6","doi-asserted-by":"crossref","unstructured":"Yutao Huang, Lingyang Chu, Zirui Zhou, Lanjun Wang, Jiangchuan Liu, Jian Pei, Yong Zhang, Personalized cross-silo federated learning on non-iid data, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35, 2021, pp. 7865\u20137873.","DOI":"10.1609\/aaai.v35i9.16960"},{"key":"10.1016\/j.comcom.2026.108552_b7","doi-asserted-by":"crossref","DOI":"10.1016\/j.comcom.2025.108053","article-title":"A two-stage federated learning method for personalization via selective collaboration","volume":"232","author":"Xu","year":"2025","journal-title":"Comput. Commun."},{"key":"10.1016\/j.comcom.2026.108552_b8","first-page":"23309","article-title":"Partialfed: Cross-domain personalized federated learning via partial initialization","volume":"34","author":"Sun","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.comcom.2026.108552_b9","series-title":"On bridging generic and personalized federated learning for image classification","author":"Chen","year":"2021"},{"issue":"14","key":"10.1016\/j.comcom.2026.108552_b10","doi-asserted-by":"crossref","first-page":"12749","DOI":"10.1109\/JIOT.2023.3254052","article-title":"FedFTHA: A fine-tuning and head aggregation method in federated learning","volume":"10","author":"Wang","year":"2023","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.comcom.2026.108552_b11","doi-asserted-by":"crossref","unstructured":"Xiyuan Yang, Wenke Huang, Mang Ye, Fedas: Bridging inconsistency in personalized federated learning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 11986\u201311995.","DOI":"10.1109\/CVPR52733.2024.01139"},{"key":"10.1016\/j.comcom.2026.108552_b12","doi-asserted-by":"crossref","unstructured":"Q. Yang, Y. Liu, T. Chen, Y. Tong, Federated machine learning: Concept and applications. ACM transactions on intelligent systems and technology, 10 (2) (2019) 1\u201319.","DOI":"10.1145\/3298981"},{"issue":"3","key":"10.1016\/j.comcom.2026.108552_b13","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1109\/MSP.2020.2975749","article-title":"Federated learning: Challenges, methods, and future directions","volume":"37","author":"Li","year":"2020","journal-title":"IEEE Signal Process. Mag."},{"key":"10.1016\/j.comcom.2026.108552_b14","series-title":"2021 IEEE 41st International Conference on Distributed Computing Systems Workshops","first-page":"27","article-title":"Personalized federated learning by structured and unstructured pruning under data heterogeneity","author":"Vahidian","year":"2021"},{"key":"10.1016\/j.comcom.2026.108552_b15","series-title":"On the convergence of fedavg on non-iid data","author":"Li","year":"2019"},{"key":"10.1016\/j.comcom.2026.108552_b16","doi-asserted-by":"crossref","unstructured":"P Kairouz, HB McMahan, B Avent, A Bellet, M Bennis, AN Bhagoji, K Bonawitz, Z Charles, G Cormode, R Cummings, et al. Advances and open problems in federated learning. Foundations and Trends\u00ae in Machine Learning, 14 (1\u20132), 1\u2013210. Preprint available on arXiv: arXiv, 2021.","DOI":"10.1561\/2200000083"},{"key":"10.1016\/j.comcom.2026.108552_b17","series-title":"Personalized federated learning with first order model optimization","author":"Zhang","year":"2020"},{"key":"10.1016\/j.comcom.2026.108552_b18","series-title":"Federated learning of a mixture of global and local models","author":"Hanzely","year":"2020"},{"key":"10.1016\/j.comcom.2026.108552_b19","series-title":"Three approaches for personalization with applications to federated learning","author":"Mansour","year":"2020"},{"key":"10.1016\/j.comcom.2026.108552_b20","series-title":"Adaptive personalized federated learning","author":"Deng","year":"2020"},{"key":"10.1016\/j.comcom.2026.108552_b21","unstructured":"Xinghao Wu, Xuefeng Liu, Jianwei Niu, Guogang Zhu, Shaojie Tang, Bold but cautious: Unlocking the potential of personalized federated learning through cautiously aggressive collaboration, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 19375\u201319384."},{"key":"10.1016\/j.comcom.2026.108552_b22","doi-asserted-by":"crossref","unstructured":"Jianqing Zhang, Yang Hua, Hao Wang, Tao Song, Zhengui Xue, Ruhui Ma, Haibing Guan, Fedala: Adaptive local aggregation for personalized federated learning, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 37, 2023, pp. 11237\u201311244.","DOI":"10.1609\/aaai.v37i9.26330"},{"key":"10.1016\/j.comcom.2026.108552_b23","doi-asserted-by":"crossref","DOI":"10.1016\/j.jnca.2023.103714","article-title":"A systematic review of federated learning: Challenges, aggregation methods, and development tools","volume":"220","author":"Guendouzi","year":"2023","journal-title":"J. Netw. Comput. Appl."},{"key":"10.1016\/j.comcom.2026.108552_b24","doi-asserted-by":"crossref","unstructured":"Liping Yi, Gang Wang, Xiaoguang Liu, Zhuan Shi, Han Yu, Fedgh: Heterogeneous federated learning with generalized global header, in: Proceedings of the 31st ACM International Conference on Multimedia, 2023, pp. 8686\u20138696.","DOI":"10.1145\/3581783.3611781"},{"key":"10.1016\/j.comcom.2026.108552_b25","first-page":"4175","article-title":"Balanced meta-softmax for long-tailed visual recognition","volume":"33","author":"Ren","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.comcom.2026.108552_b26","series-title":"Identifying and compensating for feature deviation in imbalanced deep learning","author":"Ye","year":"2020"},{"key":"10.1016\/j.comcom.2026.108552_b27","series-title":"Personalized federated learning with feature alignment and classifier collaboration","author":"Xu","year":"2023"},{"key":"10.1016\/j.comcom.2026.108552_b28","series-title":"Fashion-mnist: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017"},{"key":"10.1016\/j.comcom.2026.108552_b29","series-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"10.1016\/j.comcom.2026.108552_b30","series-title":"International Conference on Machine Learning","first-page":"9489","article-title":"Personalized federated learning using hypernetworks","author":"Shamsian","year":"2021"},{"key":"10.1016\/j.comcom.2026.108552_b31","first-page":"2351","article-title":"Ensemble distillation for robust model fusion in federated learning","volume":"33","author":"Lin","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.comcom.2026.108552_b32","series-title":"Federated learning with personalization layers","author":"Arivazhagan","year":"2019"},{"key":"10.1016\/j.comcom.2026.108552_b33","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.comcom.2026.108552_b34","series-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"10.1016\/j.comcom.2026.108552_b35","doi-asserted-by":"crossref","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["Computer Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0140366426001428?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0140366426001428?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T06:16:08Z","timestamp":1783145768000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0140366426001428"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":35,"alternative-id":["S0140366426001428"],"URL":"https:\/\/doi.org\/10.1016\/j.comcom.2026.108552","relation":{},"ISSN":["0140-3664"],"issn-type":[{"value":"0140-3664","type":"print"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Personalized federated learning with two-stage adaptive aggregation under global feature constraints","name":"articletitle","label":"Article Title"},{"value":"Computer Communications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.comcom.2026.108552","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":"108552"}}