{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,31]],"date-time":"2026-05-31T11:00:40Z","timestamp":1780225240958,"version":"3.54.0"},"reference-count":50,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.knosys.2026.116014","type":"journal-article","created":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T15:08:32Z","timestamp":1777129712000},"page":"116014","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["FLEX: Robust client selection for dynamic federated learning environments"],"prefix":"10.1016","volume":"344","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7993-5276","authenticated-orcid":false,"given":"Mao","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6876-1795","authenticated-orcid":false,"given":"Weiwei","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1409-2623","authenticated-orcid":false,"given":"Dongdong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3215-5157","authenticated-orcid":false,"given":"James Z.","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.116014_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.adhoc.2023.103320","article-title":"Blockchain and federated learning-based intrusion detection approaches for edge-enabled industrial IoT networks: A survey","volume":"152","author":"Ali","year":"2024","journal-title":"Ad Hoc Netw."},{"key":"10.1016\/j.knosys.2026.116014_b2","doi-asserted-by":"crossref","first-page":"6693","DOI":"10.1109\/TIFS.2024.3420126","article-title":"A robust privacy-preserving federated learning model against model poisoning attacks","volume":"19","author":"Yazdinejad","year":"2024","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"issue":"3","key":"10.1016\/j.knosys.2026.116014_b3","doi-asserted-by":"crossref","first-page":"5983","DOI":"10.1109\/TCE.2024.3385440","article-title":"A review of federated learning methods in heterogeneous scenarios","volume":"70","author":"Pei","year":"2024","journal-title":"IEEE Trans. Consum. Electron."},{"key":"10.1016\/j.knosys.2026.116014_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.102189","article-title":"Federated learning for IoT devices: Enhancing TinyML with on-board training","volume":"104","author":"Ficco","year":"2024","journal-title":"Inf. Fusion"},{"issue":"12","key":"10.1016\/j.knosys.2026.116014_b5","doi-asserted-by":"crossref","DOI":"10.1145\/3679013","article-title":"When federated learning meets privacy-preserving computation","volume":"56","author":"Chen","year":"2024","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.knosys.2026.116014_b6","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1016\/j.future.2023.09.008","article-title":"Model aggregation techniques in federated learning: A comprehensive survey","volume":"150","author":"Qi","year":"2024","journal-title":"Future Gener. Comput. Syst."},{"key":"10.1016\/j.knosys.2026.116014_b7","series-title":"Proceedings of the 33rd International Joint Conference on Artificial Intelligence","first-page":"4760","article-title":"FedGCS: A generative framework for efficient client selection in federated learning via gradient-based optimization","author":"Ning","year":"2024"},{"issue":"12","key":"10.1016\/j.knosys.2026.116014_b8","doi-asserted-by":"crossref","first-page":"9387","DOI":"10.1109\/TPAMI.2024.3418862","article-title":"Federated learning for generalization, robustness, fairness: A survey and benchmark","volume":"46","author":"Huang","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"11","key":"10.1016\/j.knosys.2026.116014_b9","doi-asserted-by":"crossref","first-page":"19188","DOI":"10.1109\/JIOT.2024.3376548","article-title":"Federated learning with non-IID data: A survey","volume":"11","author":"Lu","year":"2024","journal-title":"IEEE Internet Things J."},{"issue":"8","key":"10.1016\/j.knosys.2026.116014_b10","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1007\/s10462-024-10846-8","article-title":"An overview of implementing security and privacy in federated learning","volume":"57","author":"Hu","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"10.1016\/j.knosys.2026.116014_b11","doi-asserted-by":"crossref","DOI":"10.1016\/j.ress.2024.109950","article-title":"Multi-hop graph pooling adversarial network for cross-domain remaining useful life prediction: A distributed federated learning perspective","volume":"244","author":"Zhang","year":"2024","journal-title":"Reliab. Eng. Syst. Saf."},{"issue":"4","key":"10.1016\/j.knosys.2026.116014_b12","doi-asserted-by":"crossref","first-page":"2879","DOI":"10.1109\/TETCI.2024.3500009","article-title":"EarlyBirdFL: Leveraging early bird ticket networks for enhanced personalized learning","volume":"9","author":"Li","year":"2025","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"issue":"5","key":"10.1016\/j.knosys.2026.116014_b13","doi-asserted-by":"crossref","first-page":"3426","DOI":"10.1109\/TETCI.2025.3526941","article-title":"SynFlowFL: A dynamic synaptic flow framework for efficient, personalized federated learning","volume":"9","author":"Li","year":"2025","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"10.1016\/j.knosys.2026.116014_b14","series-title":"Proceedings of the 42nd IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4978","article-title":"Federated learning with domain shift eraser","author":"Wang","year":"2025"},{"key":"10.1016\/j.knosys.2026.116014_b15","series-title":"Proceedings of the 41st IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"26233","article-title":"An aggregation-free federated learning for tackling data heterogeneity","author":"Wang","year":"2024"},{"key":"10.1016\/j.knosys.2026.116014_b16","doi-asserted-by":"crossref","DOI":"10.1016\/j.sysarc.2024.103088","article-title":"Hybrid privacy preserving federated learning against irregular users in next-generation internet of things","volume":"148","author":"Yazdinejad","year":"2024","journal-title":"J. Syst. Archit."},{"key":"10.1016\/j.knosys.2026.116014_b17","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1016\/j.future.2024.05.006","article-title":"Multi-task federated learning-based system anomaly detection and multi-classification for microservices architecture","volume":"159","author":"Hao","year":"2024","journal-title":"Future Gener. Comput. Syst."},{"key":"10.1016\/j.knosys.2026.116014_b18","series-title":"Proceedings of the 41st IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11986","article-title":"FedAS: Bridging inconsistency in personalized federated learning","author":"Yang","year":"2024"},{"issue":"2","key":"10.1016\/j.knosys.2026.116014_b19","doi-asserted-by":"crossref","first-page":"37","DOI":"10.4236\/jcc.2025.132004","article-title":"Beyond the cloud: Federated learning and edge AI for the next decade","volume":"13","author":"Thomas","year":"2025","journal-title":"J. Comput. Commun."},{"issue":"4","key":"10.1016\/j.knosys.2026.116014_b20","doi-asserted-by":"crossref","first-page":"817","DOI":"10.1109\/JSAC.2023.3345431","article-title":"Personalized federated learning with model-contrastive learning for multi-modal user modeling in human-centric metaverse","volume":"42","author":"Zhou","year":"2024","journal-title":"IEEE J. Sel. Areas Commun."},{"key":"10.1016\/j.knosys.2026.116014_b21","series-title":"Proceedings of the 38th International Conference on Neural Information Processing Systems","first-page":"111106","article-title":"FedLLM-Bench: Realistic benchmarks for federated learning of large language models","author":"Ye","year":"2024"},{"issue":"5","key":"10.1016\/j.knosys.2026.116014_b22","doi-asserted-by":"crossref","first-page":"9180","DOI":"10.1109\/TNNLS.2024.3438843","article-title":"FedSTS: A stratified client selection framework for consistently fast federated learning","volume":"36","author":"Gao","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.knosys.2026.116014_b23","series-title":"Proceedings of the 39th IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10102","article-title":"FedCor: Correlation-based active client selection strategy for heterogeneous federated learning","author":"Tang","year":"2022"},{"key":"10.1016\/j.knosys.2026.116014_b24","series-title":"Proceedings of the 41st International Conference on Computer Design","first-page":"444","article-title":"Flash-RL: Federated learning addressing system and static heterogeneity using reinforcement learning","author":"Bouaziz","year":"2023"},{"key":"10.1016\/j.knosys.2026.116014_b25","series-title":"Proceedings of the 10th International Conference on Learning Representations","article-title":"Looking back on learned experiences for class\/task incremental learning","author":"PourKeshavarz","year":"2022"},{"key":"10.1016\/j.knosys.2026.116014_b26","series-title":"Proceedings of the 39th IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10154","article-title":"Federated class-incremental learning","author":"Dong","year":"2022"},{"key":"10.1016\/j.knosys.2026.116014_b27","series-title":"Proceedings of the 38th International Conference on Machine Learning","first-page":"12073","article-title":"Federated continual learning with weighted inter-client transfer","author":"Yoon","year":"2021"},{"key":"10.1016\/j.knosys.2026.116014_b28","series-title":"Proceedings of the 74th International Conference on IEEE International Symposium on Information Theory","first-page":"1848","article-title":"Fed-IT: Addressing class imbalance in federated learning through an information-theoretic lens","author":"Hamidi","year":"2024"},{"issue":"11","key":"10.1016\/j.knosys.2026.116014_b29","first-page":"10165","article-title":"Addressing class imbalance in federated learning","volume":"35","author":"Wang","year":"2021","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.knosys.2026.116014_b30","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/j.future.2023.09.019","article-title":"FL-IIDS: A novel federated learning-based incremental intrusion detection system","volume":"151","author":"Jin","year":"2024","journal-title":"Future Gener. Comput. Syst."},{"key":"10.1016\/j.knosys.2026.116014_b31","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.123553","article-title":"Towards optimal learning: Investigating the impact of different model updating strategies in federated learning","volume":"249","author":"Ili\u0107","year":"2024","journal-title":"Expert Syst. Appl."},{"issue":"9","key":"10.1016\/j.knosys.2026.116014_b32","doi-asserted-by":"crossref","first-page":"16364","DOI":"10.1109\/JIOT.2024.3353793","article-title":"SLMFed: A stage-based and layerwise mechanism for incremental federated learning to assist dynamic and ubiquitous IOT","volume":"11","author":"You","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.knosys.2026.116014_b33","series-title":"Proceedings of the 18th International Conference on European Conference on Computer Vision","first-page":"127","article-title":"Personalized federated domain-incremental learning based on adaptive knowledge matching","author":"Li","year":"2024"},{"key":"10.1016\/j.knosys.2026.116014_b34","doi-asserted-by":"crossref","DOI":"10.1016\/j.automatica.2023.111460","article-title":"SHED: A Newton-type algorithm for federated learning based on incremental hessian eigenvector sharing","volume":"160","author":"Dal Fabbro","year":"2024","journal-title":"Automatica"},{"key":"10.1016\/j.knosys.2026.116014_b35","series-title":"Proceedings of the 39th IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10164","article-title":"Federated class-incremental learning","author":"Dong","year":"2022"},{"key":"10.1016\/j.knosys.2026.116014_b36","series-title":"Proceedings of the 74th International Conference on IEEE International Symposium on Information Theory","first-page":"1848","article-title":"Fed-IT: Addressing class imbalance in federated learning through an information-theoretic lens","author":"Hamidi","year":"2024"},{"issue":"2","key":"10.1016\/j.knosys.2026.116014_b37","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1109\/LNET.2024.3363620","article-title":"Greedy Shapley client selection for communication-efficient federated learning","volume":"6","author":"Singhal","year":"2024","journal-title":"IEEE Netw. Lett."},{"key":"10.1016\/j.knosys.2026.116014_b38","series-title":"Proceedings of the 10th International Conference on Learning Representations","article-title":"Diverse client selection for federated learning via submodular maximization","author":"Balakrishnan","year":"2022"},{"issue":"1\u20132","key":"10.1016\/j.knosys.2026.116014_b39","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2200000068","article-title":"Introduction to multi-armed bandits","volume":"12","author":"Slivkins","year":"2019","journal-title":"Found. Trends Mach. Learn."},{"issue":"1","key":"10.1016\/j.knosys.2026.116014_b40","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1137\/S0097539701398375","article-title":"The nonstochastic multiarmed bandit problem","volume":"32","author":"Auer","year":"2002","journal-title":"SIAM J. Comput."},{"issue":"4","key":"10.1016\/j.knosys.2026.116014_b41","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2523813","article-title":"A survey on concept drift adaptation","volume":"46","author":"Gama","year":"2014","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.knosys.2026.116014_b42","series-title":"Proceedings of the 2023 IEEE Conference on Computer Communications","first-page":"1","article-title":"Asynchronous federated unlearning","author":"Su","year":"2023"},{"key":"10.1016\/j.knosys.2026.116014_b43","series-title":"Proceedings of the 2020Machine Learning and Systems","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume":"vol. 2","author":"Li","year":"2020"},{"issue":"3","key":"10.1016\/j.knosys.2026.116014_b44","doi-asserted-by":"crossref","first-page":"324","DOI":"10.1145\/1147954.1147956","article-title":"Dependent rounding and its applications to approximation algorithms","volume":"53","author":"Gandhi","year":"2006","journal-title":"J. ACM","ISSN":"https:\/\/id.crossref.org\/issn\/0004-5411","issn-type":"print"},{"key":"10.1016\/j.knosys.2026.116014_b45","series-title":"Proceedings of the 20th International Conference on Artificial Intelligence and Statistics","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"McMahan","year":"2017"},{"issue":"6","key":"10.1016\/j.knosys.2026.116014_b46","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.2026.116014_b47","series-title":"Proceedings of the 38th International Conference on Machine Learning","first-page":"3407","article-title":"Clustered sampling: Low-variance and improved representativity for clients selection in federated learning","author":"Fraboni","year":"2021"},{"key":"10.1016\/j.knosys.2026.116014_b48","doi-asserted-by":"crossref","DOI":"10.1016\/j.cose.2025.104642","article-title":"FELACS: Federated learning with adaptive client selection for IoT DDoS attack detection","volume":"158","author":"Anley","year":"2025","journal-title":"Comput. Secur."},{"key":"10.1016\/j.knosys.2026.116014_b49","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.126891","article-title":"Interpretable machine learning assessment","volume":"561","author":"Han","year":"2023","journal-title":"Neurocomputing"},{"issue":"100","key":"10.1016\/j.knosys.2026.116014_b50","first-page":"1","article-title":"Fedlab: A flexible federated learning framework","volume":"24","author":"Zeng","year":"2023","journal-title":"J. Mach. Learn. Res."}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126007409?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126007409?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,31]],"date-time":"2026-05-31T10:05:00Z","timestamp":1780221900000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126007409"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":50,"alternative-id":["S0950705126007409"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116014","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"FLEX: Robust client selection for dynamic federated learning environments","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116014","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":"116014"}}