{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T16:06:07Z","timestamp":1779120367290,"version":"3.51.4"},"reference-count":42,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T00:00:00Z","timestamp":1768780800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["4252030"],"award-info":[{"award-number":["4252030"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,16]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Personalized federated learning aims to deliver customized models for clients with heterogeneous data distributions while preserving data privacy. In this work, we propose personalized federated learning with feature complementarity and temporal regularization (pFedCT), a novel PFL framework where each client adopts a broad learning system (BLS) as the local model. Indeed, the existing BLS-based FL methods have been successful in enhancing communication efficiency, privacy preservation, and Byzantine robustness, but they often fail to address the critical issue of personalization. To achieve effective personalization, pFedCT introduces two key components. First, we extract feature node matrices from each client\u2019s BLS model, which capture the internal feature representations of local data. By comparing the principal subspaces of these matrices, we assess the complementarity between clients\u2019 learned representations. This enables each client to collaborate with others who provide diverse and informative knowledge. Second, we incorporate a temporal regularization mechanism to stabilize the collaboration structure across communication rounds, mitigating performance degradation caused by fluctuating local updates and data shifts. Extensive experiments on Modified National Institute of Standards and Technology (MNIST) and Fashion-MNIST datasets under both independent and identically distributed (IID) and non-IID settings demonstrate that pFedCT consistently outperforms existing BLS-based baselines and achieves competitive accuracy compared to deep neural network-based methods, while maintaining superior efficiency in communication and computation.<\/jats:p>","DOI":"10.1093\/comjnl\/bxaf148","type":"journal-article","created":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T12:42:32Z","timestamp":1767184952000},"page":"838-851","source":"Crossref","is-referenced-by-count":0,"title":["Personalized federated learning with feature complementarity and temporal regularization"],"prefix":"10.1093","volume":"69","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7348-6337","authenticated-orcid":false,"given":"Chang-E","family":"Ren","sequence":"first","affiliation":[{"name":"Information Engineering College, Capital Normal University , 105 West Third Ring Road North, 100048 Beijing ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1971-0480","authenticated-orcid":false,"given":"Weidong","family":"Jia","sequence":"additional","affiliation":[{"name":"Information Engineering College, Capital Normal University , 105 West Third Ring Road North, 100048 Beijing ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2026,1,19]]},"reference":[{"key":"2026051811064510800_ref1","doi-asserted-by":"crossref","first-page":"344","DOI":"10.1504\/IJBET.2009.027798","article-title":"Light propagation through biological tissue: Comparison between Monte Carlo simulation and deterministic models","volume":"2","author":"Kumar","year":"2009","journal-title":"Int J Biomed Eng Technol"},{"key":"2026051811064510800_ref2","article-title":"Effectiveness of passive thermography in predicting mucositis in head and neck cancer patients using light-weight","volume-title":"Proceedings of the 12th International Conference on Frontiers in Intelligent Computing: Theory and Applications (FICTA)","author":"Ruchika","year":"2025"},{"key":"2026051811064510800_ref3","doi-asserted-by":"publisher","DOI":"10.12694\/scpe.v26i2.3924","article-title":"Classification of royal delicious apples using hybrid feature selection and feature weighting method based on svm classifier","volume":"26","author":"Kaur","year":"2025","journal-title":"Scalable Comput Pract Exper"},{"key":"2026051811064510800_ref4","article-title":"Robust feature extraction from omnidirectional outdoor images for computer vision applications","volume":"10","author":"Aggarwal","year":"2025","journal-title":"Int J Instrum Meas"},{"key":"2026051811064510800_ref5","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (PMLR)","author":"McMahan","year":"2017"},{"key":"2026051811064510800_ref6","doi-asserted-by":"crossref","first-page":"128497","DOI":"10.1016\/j.eswa.2025.128497","article-title":"ZO-APFPG: a provably zeroth-order adaptive personalized federated policy gradient algorithm for reinforcement learning with environment heterogeneity","volume":"291","author":"Feng","year":"2025","journal-title":"Expert Syst Appl"},{"key":"2026051811064510800_ref7","article-title":"Personalized subgraph federated learning","volume-title":"Proceedings of the 10th International Conference on International Conference on Machine Learning (ICLR)","author":"Baek","year":"2022"},{"key":"2026051811064510800_ref8","doi-asserted-by":"crossref","first-page":"3710","DOI":"10.1109\/TNNLS.2020.3015958","article-title":"Clustered federated learning: Model-agnostic distributed multitask optimization under privacy constraints","volume":"32","author":"Sattler","year":"2021","journal-title":"IEEE Trans Neural Networks Learn Syst"},{"key":"2026051811064510800_ref9","article-title":"Personalized federated learning with inferred collaboration graphs","volume-title":"Proceedings of the 40th International Conference on Machine Learning (ICML)","author":"Ye","year":"2023"},{"key":"2026051811064510800_ref10","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v39i21.34429","article-title":"Asynchronous federated clustering with unknown number of clusters","volume-title":"Proceedings of the 39th International Conference on AAAI Conference on Artificial Intelligence (AAAI)","author":"Zhang","year":"2025"},{"key":"2026051811064510800_ref11","article-title":"Measuring the effects of non-identical data distribution for federated visual classification","author":"Hsu","year":"2019"},{"key":"2026051811064510800_ref12","article-title":"FedMix: approximation of mixup under mean augmented federated learning","volume-title":"Proceedings of the 9th International Conference on Learning Representations (ICLR)","author":"Yoon","year":"2021"},{"key":"2026051811064510800_ref13","article-title":"Heterogeneous personalized federated learning by local-global updates mixing via convergence rate","volume-title":"Proceedings of the 12th International Conference on Learning Representations (ICLR)","author":"Jiang","year":"2024"},{"key":"2026051811064510800_ref14","article-title":"Personalized federated learning with moreau envelopes","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems (NeurIPS)","author":"Dinh","year":"2020"},{"key":"2026051811064510800_ref15","article-title":"Ditto: fair and robust federated learning through personalization","volume-title":"Proceedings of the 38th International Conference on Machine Learning (ICLR)","author":"Li","year":"2021"},{"key":"2026051811064510800_ref16","doi-asserted-by":"publisher","first-page":"35956","DOI":"10.1109\/JIOT.2025.3581223","article-title":"Personalized federated transfer learning based on global synthetic data for battery state of health estimation","volume":"12","author":"Yuan","year":"2025","journal-title":"IEEE Internet Things J"},{"key":"2026051811064510800_ref17","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v39i18.34172","article-title":"FedSPU: personalized federated learning for resource-constrained devices with stochastic parameter update","volume-title":"Proceedings of the 39th International Conference on AAAI Conference on Artificial Intelligence (AAAI)","author":"Niu","year":"2025"},{"key":"2026051811064510800_ref18","article-title":"PFEDEDIT: personalized federated learning via automated model editing","volume-title":"Proceedings of the 18th European Conference on Computer Vision (ECCV)","author":"Yuan","year":"2024"},{"key":"2026051811064510800_ref19","doi-asserted-by":"publisher","first-page":"113073","DOI":"10.1016\/j.knosys.2025.113073","article-title":"Personalized federated learning with multiple classifier aggregation","volume":"311","author":"Zheng","year":"2025","journal-title":"Knowledge-Based Syst"},{"key":"2026051811064510800_ref20","doi-asserted-by":"crossref","first-page":"114218","DOI":"10.1016\/j.knosys.2025.114218","article-title":"FedECP: enhancing global collaboration and local personalization for personalized federated learning","volume":"328","author":"Yingxun","year":"2025","journal-title":"Knowledge-Based Syst"},{"key":"2026051811064510800_ref21","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1007\/s10586-024-04841-5","article-title":"FedGAC: optimizing generalization in personalized federated learning via adaptive initialization and strategic client selection","volume":"28","author":"Yichun","year":"2025","journal-title":"Clust Comput"},{"key":"2026051811064510800_ref22","doi-asserted-by":"crossref","first-page":"7709","DOI":"10.1109\/TMC.2025.3552982","article-title":"Reads: a personalized federated learning framework with fine-grained layer aggregation and decentralized clustering","volume":"24","author":"Haoyu","year":"2025","journal-title":"IEEE Trans Mob Comput"},{"key":"2026051811064510800_ref23","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP49660.2025.10890286","article-title":"GradPFL: gradient-driven adaptive clustering in personalized federated learning","volume-title":"Proceedings of the 50th International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Song","year":"2025"},{"key":"2026051811064510800_ref24","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1109\/TNNLS.2017.2716952","article-title":"Broad learning system: an effective and efficient incremental learning system without the need for deep architecture","volume":"29","author":"Philip Chen","year":"2018","journal-title":"IEEE Trans Neural Networks Learn Syst"},{"key":"2026051811064510800_ref25","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proc IEEE"},{"key":"2026051811064510800_ref26","article-title":"Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017"},{"key":"2026051811064510800_ref27","article-title":"Exploiting shared representations for personalized federated learning","volume-title":"Proceedings of the 38th International Conference on Machine Learning (PMLR)","author":"Collins","year":"2021"},{"key":"2026051811064510800_ref28","article-title":"Personalized federated learning with theoretical guarantees: a model-agnostic meta-learning approach","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems (NeurIPS)","author":"Fallah","year":"2020"},{"key":"2026051811064510800_ref29","article-title":"Federated optimization in heterogeneous networks","volume-title":"Proceedings of the 3th Conference on Machine Learning and Systems","author":"Li","year":"2020"},{"key":"2026051811064510800_ref30","article-title":"Adaptive personalized federated learning","author":"Deng","year":"2020"},{"key":"2026051811064510800_ref31","article-title":"Federated learning with personalization layers","author":"Arivazhagan","year":"2019"},{"key":"2026051811064510800_ref32","article-title":"FedBN: federated learning on non-IID features via local batch normalization","volume-title":"Proceedings of the 9th International Conference on International Conference on Machine Learning (ICLR)","author":"Li","year":"2021"},{"key":"2026051811064510800_ref33","first-page":"400","article-title":"FeDU: a unified framework for federated multi-task learning with laplacian regularization","author":"Dinh","year":"2021"},{"key":"2026051811064510800_ref34","doi-asserted-by":"publisher","first-page":"3042","DOI":"10.1109\/TNNLS.2023.3344084","article-title":"Allosteric feature collaboration for model-heterogeneous federated learning","volume":"36","author":"Yang","year":"2025","journal-title":"IEEE Trans Neural Networks Learn Syst"},{"key":"2026051811064510800_ref35","doi-asserted-by":"crossref","first-page":"102756","DOI":"10.1016\/j.inffus.2024.102756","article-title":"FairDPFL-SCS: fair dynamic personalized federated learning with strategic client selection for improved accuracy and fairness","volume":"115","author":"Sabah","year":"2025","journal-title":"Inf Fusion"},{"key":"2026051811064510800_ref36","doi-asserted-by":"crossref","first-page":"122553","DOI":"10.1016\/j.ins.2025.122553","article-title":"FedPDA: personalized federated learning based on attribute similarity migration","volume":"720","author":"Zhou","year":"2025","journal-title":"Inform Sci"},{"key":"2026051811064510800_ref37","doi-asserted-by":"crossref","first-page":"164","DOI":"10.3390\/fi16050164","article-title":"pFedBASC: personalized federated learning with blockchain-assisted semi-centralized framework","volume":"16","author":"Zhang","year":"2024","journal-title":"Future Internet"},{"key":"2026051811064510800_ref38","doi-asserted-by":"crossref","DOI":"10.1145\/3673038.3673112","article-title":"Rethinking personalized federated learning from knowledge perspective","volume-title":"Proceedings of the 53rd International Conference on Parallel Processing(ICPP)","author":"Yao","year":"2024"},{"key":"2026051811064510800_ref39","doi-asserted-by":"publisher","first-page":"3874","DOI":"10.1109\/TCYB.2021.3090260","article-title":"Federated continuous learning with broad network architecture","volume":"51","author":"Le","year":"2021","journal-title":"IEEE Trans Cybern"},{"key":"2026051811064510800_ref40","doi-asserted-by":"crossref","first-page":"110366","DOI":"10.1016\/j.knosys.2023.110366","article-title":"FBL-ET: a federated broad learning framework based on event trigger","volume":"265","author":"Ren","year":"2023","journal-title":"Knowledge-Based Syst"},{"key":"2026051811064510800_ref41","first-page":"20150202","article-title":"Principal component analysis: a review and recent developments","volume":"374","author":"Jolliffe","year":"2016","journal-title":"Philos Transact A Math Phys Eng Sci"},{"key":"2026051811064510800_ref42","article-title":"Balancing similarity and complementarity for federated learning","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Yan","year":"2024"}],"container-title":["The Computer Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/69\/5\/838\/66460979\/bxaf148.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/69\/5\/838\/66460979\/bxaf148.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T15:06:58Z","timestamp":1779116818000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/comjnl\/article\/69\/5\/838\/8429908"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,19]]},"references-count":42,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,1,19]]},"published-print":{"date-parts":[[2026,5,16]]}},"URL":"https:\/\/doi.org\/10.1093\/comjnl\/bxaf148","relation":{},"ISSN":["0010-4620","1460-2067"],"issn-type":[{"value":"0010-4620","type":"print"},{"value":"1460-2067","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,5]]},"published":{"date-parts":[[2026,1,19]]}}}