{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T16:23:38Z","timestamp":1774023818310,"version":"3.50.1"},"reference-count":44,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100017534","name":"Project 333 of Jiangsu Province","doi-asserted-by":"publisher","award":["JSGCZX23005"],"award-info":[{"award-number":["JSGCZX23005"]}],"id":[{"id":"10.13039\/501100017534","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009012","name":"Hohai University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009012","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005374","name":"Nanjing University of Posts and Telecommunications","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["B250201047"],"award-info":[{"award-number":["B250201047"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.patcog.2026.113326","type":"journal-article","created":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T08:00:14Z","timestamp":1771315214000},"page":"113326","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Dynamic federated semi-supervised learning with flexible unlabeled sample selection"],"prefix":"10.1016","volume":"177","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7375-0393","authenticated-orcid":false,"given":"Siguang","family":"Chen","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8443-8169","authenticated-orcid":false,"given":"Yanyan","family":"Xia","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6082-5955","authenticated-orcid":false,"given":"Xue","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5863-0430","authenticated-orcid":false,"given":"Chuanxin","family":"Zhao","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"4","key":"10.1016\/j.patcog.2026.113326_bib0001","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3595186","article-title":"Skin lesion intelligent diagnosis in edge computing networks: a federated contrastive learning approach","volume":"14","author":"Shi","year":"2023","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"10.1016\/j.patcog.2026.113326_bib0002","series-title":"Proc. Int. Conf. Mach. Learn. (ICML)","first-page":"160","article-title":"A unified architecture for natural language processing: deep neural networks with multitask learning","author":"Collobert","year":"2008"},{"key":"10.1016\/j.patcog.2026.113326_bib0003","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1109\/TASLP.2020.3036783","article-title":"A cross-entropy-guided measure (CEGM) for assessing speech recognition performance and optimizing DNN-based speech enhancement","volume":"29","author":"Chai","year":"2021","journal-title":"IEEE ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.patcog.2026.113326_bib0004","series-title":"Proc. Int. Conf. Electr. Energy Syst. (ICEES)","first-page":"543","article-title":"A machine learning based implementation of product and service recommendation models","author":"Mana","year":"2021"},{"key":"10.1016\/j.patcog.2026.113326_bib0005","series-title":"Proc. Int. Conf. Artif. Intell. Stat. (AISTATS)","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"Mcmahan","year":"2017"},{"key":"10.1016\/j.patcog.2026.113326_bib0006","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1109\/TMLCN.2023.3302811","article-title":"Incentivization and aggregation schemes for federated learning applications","volume":"1","author":"Hassija","year":"2023","journal-title":"IEEE. Trans. Mach. Learn. Commun. Netw."},{"issue":"3","key":"10.1016\/j.patcog.2026.113326_bib0007","doi-asserted-by":"crossref","first-page":"630","DOI":"10.1109\/TPDS.2021.3098467","article-title":"Multi-task federated learning for personalised deep neural networks in edge computing","volume":"33","author":"Mills","year":"2022","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"issue":"2","key":"10.1016\/j.patcog.2026.113326_bib0008","first-page":"1769","article-title":"Accelerating convergence of federated learning in MEC with dynamic community","volume":"23","author":"Sun","year":"2024","journal-title":"IEEE Trans. Mob. Comput."},{"key":"10.1016\/j.patcog.2026.113326_bib0009","doi-asserted-by":"crossref","first-page":"42082","DOI":"10.1109\/ACCESS.2023.3271517","article-title":"FedLC: optimizing federated learning in non-IID data via label-wise clustering","volume":"11","author":"Lee","year":"2023","journal-title":"IEEE Access"},{"key":"10.1016\/j.patcog.2026.113326_bib0010","doi-asserted-by":"crossref","first-page":"11143","DOI":"10.1016\/j.patcog.2024.111143","article-title":"FedKT: federated learning with knowledge transfer for non-IID data","volume":"159","author":"Mao","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113326_bib0011","series-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","first-page":"1","article-title":"Federated learning based on dynamic regularization","author":"Acar","year":"2021"},{"key":"10.1016\/j.patcog.2026.113326_bib0012","series-title":"Proc. IEEE Int. Conf. Data Sci. Cyberspace (DSC)","first-page":"262","article-title":"Anchor graph semi-supervised learning method based on evidence theory","author":"He","year":"2022"},{"issue":"2","key":"10.1016\/j.patcog.2026.113326_bib0013","doi-asserted-by":"crossref","first-page":"523","DOI":"10.1109\/TNNLS.2020.2995319","article-title":"Transformation-consistent self-ensembling model for semisupervised medical image segmentation","volume":"32","author":"Li","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.patcog.2026.113326_bib0014","doi-asserted-by":"crossref","first-page":"21662","DOI":"10.1109\/ACCESS.2024.3363628","article-title":"Class-wise adaptive strategy for semi supervised semantic segmentation","volume":"12","author":"Ju","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.patcog.2026.113326_bib0015","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","first-page":"14471","article-title":"Simmatch: semi-supervised learning with similarity matching","author":"Zheng","year":"2022"},{"key":"10.1016\/j.patcog.2026.113326_bib0016","doi-asserted-by":"crossref","first-page":"1639","DOI":"10.1109\/TIP.2020.3044220","article-title":"EnAET: a self-trained framework for semi-supervised and supervised learning with ensemble transformations","volume":"30","author":"Wang","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.113326_bib0017","series-title":"Proc. IEEE Int. Conf. Image Process. (ICIP)","first-page":"1136","article-title":"ActiveMatch: end-to-end semi-supervised active representation learning","author":"Yuan","year":"2022"},{"issue":"7","key":"10.1016\/j.patcog.2026.113326_bib0018","doi-asserted-by":"crossref","first-page":"1920","DOI":"10.1109\/TMI.2022.3222126","article-title":"Federated cycling (FedCy): semi-supervised federated learning of surgical phases","volume":"42","author":"Kassem","year":"2023","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.patcog.2026.113326_bib0019","series-title":"Proc. IEEE Veh. Technol. Conf. (VTC2023-Fall)","first-page":"1","article-title":"An enhancing semi-supervised federated learning framework for internet of vehicles","author":"Su","year":"2023"},{"issue":"6","key":"10.1016\/j.patcog.2026.113326_bib0020","doi-asserted-by":"crossref","first-page":"3318","DOI":"10.1109\/TMC.2021.3136853","article-title":"FedHAR: semi-supervised online learning for personalized federated human activity recognition","volume":"22","author":"Yu","year":"2023","journal-title":"IEEE Trans. Mob. Comput."},{"issue":"11","key":"10.1016\/j.patcog.2026.113326_bib0021","doi-asserted-by":"crossref","first-page":"6744","DOI":"10.1109\/TSMC.2023.3286485","article-title":"Federated active semi-supervised learning with communication efficiency","volume":"53","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"key":"10.1016\/j.patcog.2026.113326_bib0022","series-title":"Proc. Mach. Learn. Syst. (MLSys)","first-page":"429","article-title":"Federated optimization in heterogeneous networks","author":"Li","year":"2020"},{"key":"10.1016\/j.patcog.2026.113326_bib0023","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1016\/j.patrec.2024.09.024","article-title":"Personalized federated learning on long-tailed data via knowledge distillation and generated features","volume":"186","author":"Lv","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113326_bib0024","series-title":"Proc. IEEE Int. Conf. Web Serv. (ICWS)","first-page":"269","article-title":"ASPFL: efficient personalized federated learning for edge based on adaptive sparse training","author":"Jiang","year":"2023"},{"issue":"8","key":"10.1016\/j.patcog.2026.113326_bib0025","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 Netw. Learn. Syst."},{"key":"10.1016\/j.patcog.2026.113326_bib0026","doi-asserted-by":"crossref","first-page":"110542","DOI":"10.1016\/j.patcog.2024.110542","article-title":"Dynamic heterogeneous federated learning with multi-level prototypes","volume":"153","author":"Guo","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113326_bib0027","series-title":"Proc. IEEE Int. Conf. Distrib. Comput. Syst. (ICDCS)","first-page":"1","article-title":"Communication-efficient federated learning with adaptive parameter freezing","author":"Chen","year":"2021"},{"issue":"8","key":"10.1016\/j.patcog.2026.113326_bib0028","doi-asserted-by":"crossref","first-page":"1979","DOI":"10.1109\/TPAMI.2018.2858821","article-title":"Virtual adversarial training: a regularization method for supervised and semi-supervised learning","volume":"41","author":"Miyato","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113326_bib0029","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit","first-page":"3912","article-title":"WCP: worst-case perturbations for semi-supervised deep learning","author":"Zhang","year":"2020"},{"key":"10.1016\/j.patcog.2026.113326_bib0030","series-title":"Proc. Adv. Neural Inf. Proces. Syst. (NeurIPS)","first-page":"529","article-title":"Semi-supervised learning by entropy minimization","author":"Grandvalet","year":"2005"},{"key":"10.1016\/j.patcog.2026.113326_bib0031","series-title":"Proc. Adv. Neural Inf. Proces. Syst. (NeurIPS)","first-page":"1","article-title":"Mixmatch: a holistic approach to semi-supervised learning","author":"Berthelot","year":"2019"},{"key":"10.1016\/j.patcog.2026.113326_bib0032","series-title":"Proc. Adv. Neural Inf. Proces. Syst. (NeurIPS)","first-page":"1","article-title":"FixMatch: simplifying semi-supervised learning with consistency and confidence","author":"Sohn","year":"2020"},{"key":"10.1016\/j.patcog.2026.113326_bib0033","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","first-page":"15099","article-title":"Simple: similar pseudo label exploitation for semi-supervised classification","author":"Hu","year":"2021"},{"key":"10.1016\/j.patcog.2026.113326_bib0034","series-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","first-page":"1","article-title":"Federated semi-supervised learning with inter-client consistency & disjoint learning","author":"Jeong","year":"2021"},{"issue":"2","key":"10.1016\/j.patcog.2026.113326_bib0035","doi-asserted-by":"crossref","first-page":"2039","DOI":"10.1109\/TETCI.2024.3361866","article-title":"Exploitation maximization of unlabeled data for federated semi-supervised learning","volume":"9","author":"Chen","year":"2025","journal-title":"IEEE Trans. Emerg. Top. Comp. Intell."},{"issue":"2","key":"10.1016\/j.patcog.2026.113326_bib0036","doi-asserted-by":"crossref","first-page":"1060","DOI":"10.1109\/TNSE.2022.3226574","article-title":"Uncertainty minimization for personalized federated semi-supervised learning","volume":"10","author":"Shi","year":"2023","journal-title":"IEEE Trans. Netw. Sci. Eng."},{"key":"10.1016\/j.patcog.2026.113326_bib0037","series-title":"Proc. IEEE Glob. Commun. Conf. (GLOBECOM)","first-page":"1","article-title":"GDST: global distillation self-training for semi-supervised federated learning","author":"Liu","year":"2021"},{"key":"10.1016\/j.patcog.2026.113326_bib0038","unstructured":"Z. Long, J. Wang, Y. Wang, et al., FedCon: a contrastive framework for federated semi-supervised learning, arXiv preprint, arXiv: 2109.04533, 2021."},{"issue":"10","key":"10.1016\/j.patcog.2026.113326_bib0039","doi-asserted-by":"crossref","first-page":"9161","DOI":"10.1109\/JIOT.2022.3233599","article-title":"SemiPFL: personalized semi-supervised federated learning framework for edge intelligence","volume":"10","author":"Tashakori","year":"2023","journal-title":"IEEE Internet Things J."},{"issue":"7","key":"10.1016\/j.patcog.2026.113326_bib0040","doi-asserted-by":"crossref","first-page":"9395","DOI":"10.1109\/TNNLS.2022.3233093","article-title":"Balanced federated semisupervised learning with fairness-aware pseudo-labeling","volume":"35","author":"Wei","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.patcog.2026.113326_bib0041","series-title":"Proc. IEEE Int. Conf. Comput. Vision (ICCV)","first-page":"4892","article-title":"Collaborative unsupervised visual representation learning from decentralized data","author":"Zhuang","year":"2021"},{"key":"10.1016\/j.patcog.2026.113326_bib0042","series-title":"Proc. Adv. Neural Inf. Proces. Syst. (NeurIPS)","first-page":"18408","article-title":"FlexMatch: boosting semi-supervised learning with curriculum pseudo labeling","author":"Zhang","year":"2021"},{"issue":"5","key":"10.1016\/j.patcog.2026.113326_bib0043","doi-asserted-by":"crossref","first-page":"1100","DOI":"10.1109\/TAI.2024.3508654","article-title":"Analysis of an intellectual mechanism of a novel crop recommendation system using improved heuristic algorithm-based attention and cascaded deep learning network","volume":"6","author":"Akkem","year":"2025","journal-title":"IEEE Trans. Artif. Intell."},{"key":"10.1016\/j.patcog.2026.113326_bib0044","doi-asserted-by":"crossref","first-page":"20011","DOI":"10.1007\/s00521-024-10208-z","article-title":"Streamlit-based enhancing crop recommendation systems with advanced explainable artificial intelligence for smart farming","volume":"36","author":"Akkem","year":"2024","journal-title":"Neural Comput. Appl."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326002918?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326002918?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T15:46:56Z","timestamp":1774021616000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326002918"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":44,"alternative-id":["S0031320326002918"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113326","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Dynamic federated semi-supervised learning with flexible unlabeled sample selection","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113326","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"113326"}}