{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T02:02:05Z","timestamp":1780020125912,"version":"3.53.1"},"reference-count":53,"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\/100012905","name":"Department of Science and Technology of Shandong Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100012905","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.knosys.2026.116127","type":"journal-article","created":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T12:46:55Z","timestamp":1778244415000},"page":"116127","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Less is more: Clustering with adaptive probability for heterogeneous federated learning"],"prefix":"10.1016","volume":"346","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0758-8689","authenticated-orcid":false,"given":"Yunan","family":"Wei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6883-9724","authenticated-orcid":false,"given":"Shengnan","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9106-6010","authenticated-orcid":false,"given":"Chuan","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4159-3132","authenticated-orcid":false,"given":"Yiting","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5357-7442","authenticated-orcid":false,"given":"Donglong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9232-9185","authenticated-orcid":false,"given":"Minghao","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.116127_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"},{"issue":"3","key":"10.1016\/j.knosys.2026.116127_b2","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."},{"issue":"1\u20132","key":"10.1016\/j.knosys.2026.116127_b3","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.knosys.2026.116127_b4","article-title":"BR-MTFL: A novel Byzantine resilience enhanced multi-task federated learning framework for high-speed train fault diagnosis","author":"You","year":"2025","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"10.1016\/j.knosys.2026.116127_b5","series-title":"Federated Learning: Privacy and Incentive","first-page":"240","article-title":"Federated learning for open banking","author":"Long","year":"2020"},{"key":"10.1016\/j.knosys.2026.116127_b6","doi-asserted-by":"crossref","unstructured":"Q. Wang, B. Liu, Y. Li, Traceable federated continual learning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 12872\u201312881.","DOI":"10.1109\/CVPR52733.2024.01223"},{"issue":"3","key":"10.1016\/j.knosys.2026.116127_b7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3625558","article-title":"Heterogeneous federated learning: State-of-the-art and research challenges","volume":"56","author":"Ye","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.knosys.2026.116127_b8","series-title":"Proceedings of the 37th International Conference on Machine Learning","first-page":"5132","article-title":"SCAFFOLD: Stochastic controlled averaging for federated learning","volume":"vol. 119","author":"Karimireddy","year":"2020"},{"key":"10.1016\/j.knosys.2026.116127_b9","first-page":"17395","article-title":"PA3Fed: Period-aware adaptive aggregation for improved federated learning","volume":"vol. 39","author":"Huang","year":"2025"},{"key":"10.1016\/j.knosys.2026.116127_b10","doi-asserted-by":"crossref","unstructured":"W. Huang, M. Ye, B. Du, Learn from others and be yourself in heterogeneous federated learning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 10143\u201310153.","DOI":"10.1109\/CVPR52688.2022.00990"},{"key":"10.1016\/j.knosys.2026.116127_b11","article-title":"Generalizable heterogeneous federated cross-correlation and instance similarity learning","author":"Huang","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.knosys.2026.116127_b12","series-title":"Threats to federated learning: A survey","author":"Lyu","year":"2020"},{"key":"10.1016\/j.knosys.2026.116127_b13","article-title":"Deep leakage from gradients","volume":"32","author":"Zhu","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116127_b14","doi-asserted-by":"crossref","DOI":"10.1109\/TWC.2025.3544318","article-title":"Clustered federated multi-task learning: A communication-and-computation efficient sparse sharing approach","author":"Ai","year":"2025","journal-title":"IEEE Trans. Wirel. Commun."},{"key":"10.1016\/j.knosys.2026.116127_b15","doi-asserted-by":"crossref","unstructured":"M.S. Islam, S. Javaherian, F. Xu, X. Yuan, L. Chen, N.-F. Tzeng, Fedclust: Tackling data heterogeneity in federated learning through weight-driven client clustering, in: Proceedings of the 53rd International Conference on Parallel Processing, 2024, pp. 474\u2013483.","DOI":"10.1145\/3673038.3673151"},{"key":"10.1016\/j.knosys.2026.116127_b16","series-title":"2024 IEEE\/ACM 32nd International Symposium on Quality of Service","first-page":"1","article-title":"Adadp-cfl: Cluster federated learning with adaptive clipping threshold differential privacy","author":"Yang","year":"2024"},{"key":"10.1016\/j.knosys.2026.116127_b17","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1109\/OJCS.2023.3262203","article-title":"Flis: Clustered federated learning via inference similarity for Non-IID data distribution","volume":"4","author":"Morafah","year":"2023","journal-title":"IEEE Open J. Comput. Soc."},{"key":"10.1016\/j.knosys.2026.116127_b18","first-page":"10043","article-title":"Efficient distribution similarity identification in clustered federated learning via principal angles between client data subspaces","volume":"vol. 37","author":"Vahidian","year":"2023"},{"issue":"8","key":"10.1016\/j.knosys.2026.116127_b19","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":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.knosys.2026.116127_b20","doi-asserted-by":"crossref","DOI":"10.1109\/TPDS.2024.3379933","article-title":"Resource aware clustering for tackling the heterogeneity of participants in federated learning","author":"Mishra","year":"2024","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"10.1016\/j.knosys.2026.116127_b21","doi-asserted-by":"crossref","first-page":"384","DOI":"10.1016\/j.future.2024.01.005","article-title":"Privacy-preserving clustering federated learning for non-IID data","volume":"154","author":"Luo","year":"2024","journal-title":"Future Gener. Comput. Syst."},{"key":"10.1016\/j.knosys.2026.116127_b22","series-title":"Machine Learning in Medical Imaging: 10th International Workshop, MLMI 2019, Held in Conjunction with MICCAI 2019, Shenzhen, China, October 13, 2019, Proceedings 10","first-page":"133","article-title":"Privacy-preserving federated brain tumour segmentation","author":"Li","year":"2019"},{"key":"10.1016\/j.knosys.2026.116127_b23","doi-asserted-by":"crossref","unstructured":"G. Li, Y. Hu, M. Zhang, J. Liu, Q. Yin, Y. Peng, D. Dou, FedHiSyn: A hierarchical synchronous federated learning framework for resource and data heterogeneity, in: Proceedings of the 51st International Conference on Parallel Processing, 2022, pp. 1\u201311.","DOI":"10.1145\/3545008.3545065"},{"key":"10.1016\/j.knosys.2026.116127_b24","doi-asserted-by":"crossref","DOI":"10.1016\/j.future.2025.108005","article-title":"Leveraging community detection for clustered federated learning on Non-IID data: From an information-theoretic perspective","volume":"174","author":"Sun","year":"2026","journal-title":"Future Gener. Comput. Syst."},{"key":"10.1016\/j.knosys.2026.116127_b25","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1016\/j.future.2020.07.023","article-title":"A new data clustering strategy for enhancing mutual privacy in healthcare IoT systems","volume":"113","author":"Guo","year":"2020","journal-title":"Future Gener. Comput. Syst."},{"key":"10.1016\/j.knosys.2026.116127_b26","series-title":"International Conference on Machine Learning","first-page":"4772","article-title":"Catastrophic fisher explosion: Early phase fisher matrix impacts generalization","author":"Jastrzebski","year":"2021"},{"key":"10.1016\/j.knosys.2026.116127_b27","series-title":"Critical learning periods in federated learning","author":"Yan","year":"2021"},{"key":"10.1016\/j.knosys.2026.116127_b28","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume":"2","author":"Li","year":"2020","journal-title":"Proc. Mach. Learn. Syst."},{"issue":"6","key":"10.1016\/j.knosys.2026.116127_b29","doi-asserted-by":"crossref","first-page":"4723","DOI":"10.1109\/JIOT.2020.3028742","article-title":"FedMCCS: Multicriteria client selection model for optimal IoT federated learning","volume":"8","author":"AbdulRahman","year":"2020","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.knosys.2026.116127_b30","series-title":"GFL: A decentralized federated learning framework based on blockchain","author":"Hu","year":"2020"},{"key":"10.1016\/j.knosys.2026.116127_b31","doi-asserted-by":"crossref","unstructured":"X. Ouyang, Z. Xie, J. Zhou, J. Huang, G. Xing, Clusterfl: a similarity-aware federated learning system for human activity recognition, in: Proceedings of the 19th Annual International Conference on Mobile Systems, Applications, and Services, 2021, pp. 54\u201366.","DOI":"10.1145\/3458864.3467681"},{"key":"10.1016\/j.knosys.2026.116127_b32","first-page":"19586","article-title":"An efficient framework for clustered federated learning","volume":"33","author":"Ghosh","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116127_b33","unstructured":"A. Achille, M. Rovere, S. Soatto, Critical learning periods in deep networks, in: International Conference on Learning Representations, 2018."},{"key":"10.1016\/j.knosys.2026.116127_b34","series-title":"On the relation between the sharpest directions of DNN loss and the SGD step length","author":"Jastrz\u0119bski","year":"2018"},{"key":"10.1016\/j.knosys.2026.116127_b35","doi-asserted-by":"crossref","unstructured":"G. Yan, H. Wang, X. Yuan, J. Li, Criticalfl: A critical learning periods augmented client selection framework for efficient federated learning, in: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2023, pp. 2898\u20132907.","DOI":"10.1145\/3580305.3599293"},{"key":"10.1016\/j.knosys.2026.116127_b36","article-title":"More than enough is too much: Adaptive defenses against gradient leakage in production federated learning","author":"Wang","year":"2024","journal-title":"IEEE\/ACM Trans. Netw."},{"key":"10.1016\/j.knosys.2026.116127_b37","series-title":"International Conference on Machine Learning","first-page":"8252","article-title":"Data reconstruction from gradients via de-randomized local model updates","author":"Dimitrov","year":"2023"},{"key":"10.1016\/j.knosys.2026.116127_b38","doi-asserted-by":"crossref","first-page":"911","DOI":"10.1109\/TIFS.2019.2929409","article-title":"VerifyNet: Secure and verifiable federated learning","volume":"15","author":"Xu","year":"2019","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"10.1016\/j.knosys.2026.116127_b39","unstructured":"W.-C. Li, C.-H. Hsieh, Y.-L. Liu, C.-Y. Ho, P. Sun, Eluding the Sharpness of Adversarial Training: A Client-Level Evaluation for Federated Learning, in: The Twelfth International Conference on Learning Representations, ICLR, 2024."},{"key":"10.1016\/j.knosys.2026.116127_b40","article-title":"SHE: A fast and secure asynchronous federated learning algorithm with full homomorphic encryption","author":"Liu","year":"2024","journal-title":"IEEE Trans. Dependable Secur. Comput."},{"key":"10.1016\/j.knosys.2026.116127_b41","unstructured":"J. Zhao, L. Wang, J. Zhang, L. Zhang, S. Zhang, et al., Pika: A Secure and Scalable Federated Learning Platform, in: 21st USENIX Symposium on Networked Systems Design and Implementation, NSDI 24, 2024, pp. 101\u2013117."},{"key":"10.1016\/j.knosys.2026.116127_b42","series-title":"Advances in Cryptology \u2014 EUROCRYPT \u201999","first-page":"223","article-title":"Public-key cryptosystems based on composite degree residuosity classes","author":"Paillier","year":"1999"},{"issue":"8","key":"10.1016\/j.knosys.2026.116127_b43","doi-asserted-by":"crossref","first-page":"1295","DOI":"10.3390\/electronics9081295","article-title":"The k-means algorithm: A comprehensive survey and performance evaluation","volume":"9","author":"Ahmed","year":"2020","journal-title":"Electronics"},{"issue":"146","key":"10.1016\/j.knosys.2026.116127_b44","first-page":"1","article-title":"New insights and perspectives on the natural gradient method","volume":"21","author":"Martens","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.knosys.2026.116127_b45","article-title":"On spectral clustering: Analysis and an algorithm","volume":"14","author":"Ng","year":"2001","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116127_b46","doi-asserted-by":"crossref","first-page":"4574","DOI":"10.1109\/TIFS.2021.3108434","article-title":"Privacy-enhanced federated learning against poisoning adversaries","volume":"16","author":"Liu","year":"2021","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"10.1016\/j.knosys.2026.116127_b47","doi-asserted-by":"crossref","first-page":"2977","DOI":"10.1109\/TIFS.2023.3273914","article-title":"Efficient verifiable protocol for privacy-preserving aggregation in federated learning","volume":"18","author":"Eltaras","year":"2023","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"10.1016\/j.knosys.2026.116127_b48","series-title":"On the convergence of fedavg on non-IID data","author":"Li","year":"2019"},{"key":"10.1016\/j.knosys.2026.116127_b49","series-title":"Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017"},{"key":"10.1016\/j.knosys.2026.116127_b50","series-title":"Learning multiple layers of features from tiny images.(2009)","author":"Krizhevsky","year":"2009"},{"key":"10.1016\/j.knosys.2026.116127_b51","series-title":"Measuring the effects of non-identical data distribution for federated visual classification","author":"Hsu","year":"2019"},{"key":"10.1016\/j.knosys.2026.116127_b52","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116127_b53","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. 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":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126008531?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126008531?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T01:10:04Z","timestamp":1780017004000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126008531"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":53,"alternative-id":["S0950705126008531"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116127","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Less is more: Clustering with adaptive probability for heterogeneous federated learning","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116127","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":"116127"}}