{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,21]],"date-time":"2026-06-21T04:10:46Z","timestamp":1782015046300,"version":"3.54.5"},"reference-count":46,"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":[[2026,4,18]],"date-time":"2026-04-18T00:00:00Z","timestamp":1776470400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.patcog.2026.113774","type":"journal-article","created":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T06:30:08Z","timestamp":1776493808000},"page":"113774","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"PC","title":["Exploring personalized federated learning from a distribution-based perspective"],"prefix":"10.1016","volume":"179","author":[{"given":"Tianhao","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kheng Cher","family":"Yeo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sami","family":"Azam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohan","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1375-4664","authenticated-orcid":false,"given":"Hui","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianxun","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"1\u20132","key":"10.1016\/j.patcog.2026.113774_b1","first-page":"1","article-title":"Advances and open problems in federated learning","volume":"14","author":"Kairouz","year":"2021","journal-title":"Found. Trends\u00ae Mach. Learn."},{"key":"10.1016\/j.patcog.2026.113774_b2","series-title":"AISTATS","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"McMahan","year":"2017"},{"issue":"3","key":"10.1016\/j.patcog.2026.113774_b3","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.patcog.2026.113774_b4","unstructured":"H.-Y. Chen, W.-L. Chao, On Bridging Generic and Personalized Federated Learning for Image Classification, in: ICLR, 2022."},{"key":"10.1016\/j.patcog.2026.113774_b5","series-title":"ICDE","first-page":"965","article-title":"Federated learning on non-iid data silos: An experimental study","author":"Li","year":"2022"},{"key":"10.1016\/j.patcog.2026.113774_b6","unstructured":"J. Xu, X. Tong, S.-L. Huang, Personalized federated learning with feature alignment and classifier collaboration, in: ICLR, 2023."},{"key":"10.1016\/j.patcog.2026.113774_b7","doi-asserted-by":"crossref","first-page":"2399","DOI":"10.1109\/TIFS.2025.3531143","article-title":"Maximizing uncertainty for federated learning via Bayesian optimization-based model poisoning","volume":"20","author":"Aristodemou","year":"2025","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"10.1016\/j.patcog.2026.113774_b8","doi-asserted-by":"crossref","unstructured":"Y. Zhou, B. Liu, BTFL: A Bayesian-based test-time generalization method for internal and external data distributions in federated learning, in: Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V. 1, 2025, pp. 2147\u20132158.","DOI":"10.1145\/3690624.3709309"},{"key":"10.1016\/j.patcog.2026.113774_b9","series-title":"Concrete problems in AI safety","author":"Amodei","year":"2016"},{"key":"10.1016\/j.patcog.2026.113774_b10","article-title":"Federated neural nonparametric point processes","author":"Chen","year":"2025","journal-title":"Artificial Intelligence"},{"key":"10.1016\/j.patcog.2026.113774_b11","first-page":"8392","article-title":"Personalized federated learning with gaussian processes","volume":"34","author":"Achituve","year":"2021","journal-title":"NeurIPS"},{"key":"10.1016\/j.patcog.2026.113774_b12","series-title":"ICML","first-page":"26293","article-title":"Personalized federated learning via variational bayesian inference","author":"Zhang","year":"2022"},{"key":"10.1016\/j.patcog.2026.113774_b13","first-page":"8687","article-title":"Fedpop: A bayesian approach for personalised federated learning","volume":"35","author":"Kotelevskii","year":"2022","journal-title":"NeurIPS"},{"key":"10.1016\/j.patcog.2026.113774_b14","series-title":"ICML","first-page":"4629","article-title":"What are Bayesian neural network posteriors really like?","author":"Izmailov","year":"2021"},{"key":"10.1016\/j.patcog.2026.113774_b15","first-page":"9674","article-title":"Walsh-hadamard variational inference for Bayesian deep learning","volume":"33","author":"Rossi","year":"2020","journal-title":"NeurIPS"},{"key":"10.1016\/j.patcog.2026.113774_b16","volume":"vol. 4","author":"Bishop","year":"2006"},{"key":"10.1016\/j.patcog.2026.113774_b17","series-title":"AISTATS","first-page":"6459","article-title":"QLSD: Quantised langevin stochastic dynamics for Bayesian federated learning","author":"Vono","year":"2022"},{"key":"10.1016\/j.patcog.2026.113774_b18","series-title":"Bayesian personalized federated learning with shared and personalized uncertainty representations","author":"Chen","year":"2023"},{"key":"10.1016\/j.patcog.2026.113774_b19","unstructured":"Y. Wen, D. Tran, J. Ba, Batchensemble: an alternative approach to efficient ensemble and lifelong learning, in: ICLR, 2020."},{"key":"10.1016\/j.patcog.2026.113774_b20","series-title":"UAI","first-page":"1169","article-title":"Subspace inference for Bayesian deep learning","author":"Izmailov","year":"2020"},{"key":"10.1016\/j.patcog.2026.113774_b21","series-title":"ICML","first-page":"9289","article-title":"The k-tied normal distribution: A compact parameterization of Gaussian mean field posteriors in Bayesian neural networks","author":"Swiatkowski","year":"2020"},{"key":"10.1016\/j.patcog.2026.113774_b22","series-title":"ICML","first-page":"2510","article-title":"Bayesian deep learning via subnetwork inference","author":"Daxberger","year":"2021"},{"key":"10.1016\/j.patcog.2026.113774_b23","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1023\/A:1007665907178","article-title":"An introduction to variational methods for graphical models","volume":"37","author":"Jordan","year":"1999","journal-title":"Mach. Learn."},{"key":"10.1016\/j.patcog.2026.113774_b24","unstructured":"I. Higgins, L. Matthey, A. Pal, C. Burgess, X. Glorot, M. Botvinick, S. Mohamed, A. Lerchner, beta-vae: Learning basic visual concepts with a constrained variational framework, in: ICLR, 2016."},{"key":"10.1016\/j.patcog.2026.113774_b25","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","volume":"30","author":"Lakshminarayanan","year":"2017","journal-title":"NeurIPS"},{"key":"10.1016\/j.patcog.2026.113774_b26","article-title":"Bayesian compression for deep learning","volume":"30","author":"Louizos","year":"2017","journal-title":"NeurIPS"},{"key":"10.1016\/j.patcog.2026.113774_b27","series-title":"ICML","first-page":"1607","article-title":"Variational inference for sparse and undirected models","author":"Ingraham","year":"2017"},{"key":"10.1016\/j.patcog.2026.113774_b28","series-title":"ICML","first-page":"2782","article-title":"Efficient and scalable bayesian neural nets with rank-1 factors","author":"Dusenberry","year":"2020"},{"key":"10.1016\/j.patcog.2026.113774_b29","series-title":"AISTATS","first-page":"73","article-title":"Handling sparsity via the horseshoe","author":"Carvalho","year":"2009"},{"key":"10.1016\/j.patcog.2026.113774_b30","first-page":"466","article-title":"Efficient variational inference for sparse deep learning with theoretical guarantee","volume":"33","author":"Bai","year":"2020","journal-title":"NeurIPS"},{"issue":"11","key":"10.1016\/j.patcog.2026.113774_b31","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":"1998","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.patcog.2026.113774_b32","series-title":"Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017"},{"key":"10.1016\/j.patcog.2026.113774_b33","series-title":"Learning Multiple Layers of Features from Tiny Images","author":"Krizhevsky","year":"2009"},{"key":"10.1016\/j.patcog.2026.113774_b34","first-page":"21394","article-title":"Personalized federated learning with moreau envelopes","volume":"33","author":"T. Dinh","year":"2020","journal-title":"NeurIPS"},{"key":"10.1016\/j.patcog.2026.113774_b35","article-title":"FedSI: Federated subnetwork inference for efficient uncertainty quantification","author":"Chen","year":"2025","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"10.1016\/j.patcog.2026.113774_b36","series-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"10.1016\/j.patcog.2026.113774_b37","doi-asserted-by":"crossref","unstructured":"R.T. McAllister, Y. Gal, A. Kendall, M. Van Der Wilk, A. Shah, R. Cipolla, A. Weller, Concrete problems for autonomous vehicle safety: Advantages of Bayesian deep learning, in: IJCAI, 2017.","DOI":"10.24963\/ijcai.2017\/661"},{"key":"10.1016\/j.patcog.2026.113774_b38","series-title":"Informative priors improve the reliability of multimodal clinical data classification","author":"Lopez","year":"2023"},{"key":"10.1016\/j.patcog.2026.113774_b39","unstructured":"L. Cao, H. Chen, X. Fan, J. Gama, Y.-S. Ong, V. Kumar, Bayesian federated learning: a survey, in: 32nd International Joint Conference on Artificial Intelligence, IJCAI 2023, 2023, pp. 7233\u20137242."},{"key":"10.1016\/j.patcog.2026.113774_b40","unstructured":"H.-Y. Chen, W.-L. Chao, Fedbe: Making Bayesian model ensemble applicable to federated learning, in: International Conference on Learning Representations, 2021."},{"issue":"1","key":"10.1016\/j.patcog.2026.113774_b41","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TPAMI.2023.3322743","article-title":"A Bayesian federated learning framework with online laplace approximation","volume":"46","author":"Liu","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113774_b42","unstructured":"M. Al-Shedivat, J. Gillenwater, E. Xing, A. Rostamizadeh, Federated learning via posterior averaging: A new perspective and practical algorithms, in: International Conference on Learning Representations, 2021."},{"key":"10.1016\/j.patcog.2026.113774_b43","unstructured":"H. Guo, P. Greengard, H. Wang, A. Gelman, Y. Kim, E.P. Xing, Federated learning as variational inference: A scalable expectation propagation approach, in: International Conference on Learning Representations, 2023."},{"key":"10.1016\/j.patcog.2026.113774_b44","unstructured":"H. Wang, M. Yurochkin, Y. Sun, D. Papailiopoulos, Y. Khazaeni, Federated learning with matched averaging, in: International Conference on Learning Representations, 2020."},{"issue":"1","key":"10.1016\/j.patcog.2026.113774_b45","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1007\/s10994-025-06939-2","article-title":"FedGES: A federated learning approach for Bayesian network structure learning","volume":"115","author":"Torrijos","year":"2026","journal-title":"Mach. Learn."},{"issue":"272","key":"10.1016\/j.patcog.2026.113774_b46","first-page":"1","article-title":"Fedhb: Hierarchical bayesian federated learning","volume":"26","author":"Kim","year":"2025","journal-title":"J. Mach. Learn. Res."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326007399?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326007399?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T21:48:39Z","timestamp":1780955319000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326007399"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":46,"alternative-id":["S0031320326007399"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113774","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Exploring personalized federated learning from a distribution-based perspective","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113774","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"113774"}}