{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T08:40:44Z","timestamp":1768812044977,"version":"3.49.0"},"reference-count":32,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T00:00:00Z","timestamp":1748563200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Model. Perform. Eval. Comput. Syst."],"published-print":{"date-parts":[[2025,6,30]]},"abstract":"<jats:p>In the dynamic realm of machine learning\u00a0(ML), federated learning\u00a0(FL) emerges as a pivotal method for training models on decentralized devices without the need for central data aggregation. This technique confronts the challenges of data heterogeneity, which disrupts the independent and identically distributed\u00a0(IID) assumptions, adversely affecting the accuracy of the overall model. To tackle this issue, we introduce the federated non-performing-node-resilient neural selector (FNNS), an advanced client selection algorithm grounded in a combinatorial contextual neural bandit framework. This algorithm enhances the extraction of contextual data by assessing each local client using a universally standardized dataset, thereby providing a deeper, context-specific insight suitable for federated environments. In addition, we introduce selection robustness score (SRS), a novel metric designed to quantify the efficacy of client selection in the presence of non-performing-nodes (NPN) conditions. Using this metric, we demonstrate FANS\u2019s effectiveness in enhancing the FL process. Empirical evaluations across diverse settings reveal our method\u2019s superiority over current state-of-the-art solutions, with significant improvements in both SRS and global model accuracy.<\/jats:p>","DOI":"10.1145\/3721480","type":"journal-article","created":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T11:54:24Z","timestamp":1741002864000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["An Enhanced Combinatorial Contextual Neural Bandit Approach for Client Selection in Federated Learning"],"prefix":"10.1145","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6956-3851","authenticated-orcid":false,"given":"Xiangyu","family":"Ma","sequence":"first","affiliation":[{"name":"Faculty of Engineering and Design, School of Information Technology, Carleton University, Ottawa, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3071-8350","authenticated-orcid":false,"given":"Wei","family":"Shi","sequence":"additional","affiliation":[{"name":"Faculty of Engineering and Design, School of Information Technology, Carleton University, Ottawa, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4128-1422","authenticated-orcid":false,"given":"Junfeng","family":"Wen","sequence":"additional","affiliation":[{"name":"Faculty of Engineering and Design, School of Computer Science, Carleton University, Ottawa, Canada"}]}],"member":"320","published-online":{"date-parts":[[2025,5,30]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"e_1_3_1_3_2","volume-title":"International Conference on Learning Representations","author":"Balakrishnan R.","year":"2022","unstructured":"R. Balakrishnan, T. Li, T. Zhou, N. Himayat, V. Smith, and J. Bilmes. 2022. Diverse client selection for federated learning via submodular maximization. In International Conference on Learning Representations."},{"key":"e_1_3_1_4_2","unstructured":"N. Barroso E. C\u00e1mara M. Luz\u00f3n G. G. Seco M. A. Veganzones and F. Herrera. 2020. Dynamic federated learning model for identifying adversarial clients. arxiv:2007.15030Available at https:\/\/arxiv.org\/abs\/2007.15030"},{"key":"e_1_3_1_5_2","volume-title":"Proceedings of international Workshop on Trustable, Verifiable and Auditable Federated Learning in Conjunction with AAAI","author":"Cao H.","year":"2022","unstructured":"H. Cao, Q. Pan, and J. Liu. 2022. Birds of a feather help: Context-aware client selection for federated learning. In Proceedings of international Workshop on Trustable, Verifiable and Auditable Federated Learning in Conjunction with AAAI."},{"key":"e_1_3_1_6_2","article-title":"FLASH: Federated learning across simultaneous heterogeneities","author":"Chang X.","year":"2024","unstructured":"X. Chang, S. M. Ahmed, B. Guler, S. V. Krishnamurthy, A. Swami, S. Oymak, and A. K. Roy-Chowdhury. 2024. FLASH: Federated learning across simultaneous heterogeneities. arXiv preprint:2402.08769 (2024). Available at https:\/\/arxiv.org\/abs\/2402.08769","journal-title":"arXiv preprint:2402.08769"},{"key":"e_1_3_1_7_2","volume-title":"Proceedings of 2018 First International Conference on Secure Cyber Computing and Communication (ICSCCC\u201918)","author":"Chauhan R.","year":"2018","unstructured":"R. Chauhan, K. K. Ghanshala, and R. C. Joshi. 2018. Convolutional Neural Network (CNN) for image detection and recognition. In Proceedings of 2018 First International Conference on Secure Cyber Computing and Communication (ICSCCC\u201918)."},{"key":"e_1_3_1_8_2","first-page":"5017","volume-title":"Proceedings of IEEE International Conference on Big Data","author":"Chen C.","year":"2020","unstructured":"C. Chen, Z. Chen, Y. Zhou, and B. Kailkhura. 2020. FedCluster: Boosting the convergence of federated learning via cluster-cycling. In Proceedings of IEEE International Conference on Big Data. IEEE Computer Society, Los Alamitos, CA, USA, 5017\u20135026."},{"key":"e_1_3_1_9_2","volume-title":"Proceedings of 54th Asilomar Conference on Signals, Systems, and Computers","author":"Cho Y. J.","year":"2020","unstructured":"Y. J. Cho, S. Gupta, G. Joshi, and Ya\u011fan. 2020. Bandit-based communication-efficient client selection strategies for federated learning. In Proceedings of 54th Asilomar Conference on Signals, Systems, and Computers. Pacific Grove, CA, USA."},{"key":"e_1_3_1_10_2","series-title":"Proceedings of Machine Learning Research","first-page":"10351","volume-title":"Proceedings of the 25th International Conference on Artificial Intelligence and Statistics","volume":"151","author":"Cho Y. J.","year":"2022","unstructured":"Y. J. Cho, Jianyu Wang, and G. Joshi. 2022. Towards understanding biased client selection in federated learning. In Proceedings of the 25th International Conference on Artificial Intelligence and Statistics(Proceedings of Machine Learning Research, Vol. 151), Gustau Camps-Valls, Francisco J. R. Ruiz, and Isabel Valera (Eds.). PMLR, 10351\u201310375."},{"key":"e_1_3_1_11_2","series-title":"Proceedings of Machine Learning Research","first-page":"3407","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","author":"Fraboni Y.","year":"2021","unstructured":"Y. Fraboni, R. Vidal, L. Kameni, and M. Lorenzi. 2021. Clustered sampling: Low-variance and improved representativity for clients selection in federated learning. In Proceedings of the 38th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 3407\u20133416."},{"key":"e_1_3_1_12_2","volume-title":"arXiv preprint arXiv:1909.12641","author":"Goetz J.","year":"2019","unstructured":"J. Goetz, K. Malik, D. Bui, S. Moon, H. Liu, and A. Kumar. 2019. Active federated learning. In arXiv preprint arXiv:1909.12641."},{"key":"e_1_3_1_13_2","article-title":"CIFAR-10 image classification using feature ensembles","author":"Guiste F. O.","year":"2020","unstructured":"F. O. Guiste and J. C. Vizcarra. 2020. CIFAR-10 image classification using feature ensembles. arXiv preprint:2002.03846 (2020).","journal-title":"arXiv preprint:2002.03846"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.5555\/3618408.3618987"},{"key":"e_1_3_1_15_2","unstructured":"A. Krizhevsky. 2009. Learning Multiple Layers of Features from Tiny Images. University of Toronto."},{"key":"e_1_3_1_16_2","first-page":"19","volume-title":"IProceedings of the 15th USENIX Symposium on Operating Systems Design and Implementation","author":"Lai F.","year":"2021","unstructured":"F. Lai and X. Zhu. 2021. Oort: Efficient federated learning via guided participant selection. In IProceedings of the 15th USENIX Symposium on Operating Systems Design and Implementation. USENIX Association, 19\u201335. https:\/\/www.usenix.org\/conference\/osdi21\/presentation\/lai"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1017\/9781108571401"},{"key":"e_1_3_1_18_2","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume":"54","author":"McMahan B.","year":"2017","unstructured":"B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. A. Y. Arcas. 2017. Communication-efficient learning of deep networks from decentralized data. Proceedings of the 20th International Conference on Artificial Intelligence and Statistics 54 (2017), 1273\u20131282.","journal-title":"Proceedings of the 20th International Conference on Artificial Intelligence and Statistics"},{"issue":"6","key":"e_1_3_1_19_2","doi-asserted-by":"crossref","first-page":"6538","DOI":"10.1109\/TMC.2023.3323645","article-title":"Contextual client selection for efficient federated learning over edge devices","volume":"23","author":"Pan Y.","year":"2023","unstructured":"Y. Pan, H. Cao, Y. Zhu, J. Liu, and B. Li. 2023. Contextual client selection for efficient federated learning over edge devices. IEEE Transactions on Mobile Computing 23, 6 (2023), 6538\u20136548.","journal-title":"IEEE Transactions on Mobile Computing"},{"key":"e_1_3_1_20_2","article-title":"Semi-supervised knowledge transfer for deep learning from private training data","author":"Papernot N.","year":"2017","unstructured":"N. Papernot, M. Abadi, \u00da. Erlingsson, I. Goodfellow, and K. Talwar. 2017. Semi-supervised knowledge transfer for deep learning from private training data. arXiv preprint: 1610.05755v4 (2017).","journal-title":"arXiv preprint: 1610.05755v4"},{"key":"e_1_3_1_21_2","volume-title":"2023 International Joint Conference on Neural Networks (IJCNN\u201923)","author":"Sasindran Z.","year":"2023","unstructured":"Z. Sasindran, H. Yelchuri, and T. V. Prabhakar. 2023. Ed-Fed: A generic federated learning framework with resource-aware client selection for edge devices. In 2023 International Joint Conference on Neural Networks (IJCNN\u201923)."},{"issue":"8","key":"e_1_3_1_22_2","first-page":"265","article-title":"Efficient client selection based on contextual combinatorial multi-arm bandits","volume":"22","author":"Shi F.","year":"2023","unstructured":"F. Shi, W. Lin, L. Fan, X. Lai, and X. Wang. 2023. Efficient client selection based on contextual combinatorial multi-arm bandits. IEEE Transactions on Wireless Communications 22, 8 (2023), 265\u20135277.","journal-title":"IEEE Transactions on Wireless Communications"},{"key":"e_1_3_1_23_2","article-title":"Federated model distillation with noise-free differential privacy","author":"Sun L.","year":"2021","unstructured":"L. Sun and L. Lyu. 2021. Federated model distillation with noise-free differential privacy. arXiv preprint: 2009.05537v2 (2021).","journal-title":"arXiv preprint: 2009.05537v2"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155494"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3264677"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3008091"},{"key":"e_1_3_1_27_2","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"36","author":"Yan G.","year":"2022","unstructured":"G. Yan, H. Wang, and J. Li. 2022. Seizing critical learning periods in federated learning. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36."},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599293"},{"key":"e_1_3_1_29_2","volume-title":"Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI\u201922)","author":"Zhang S. Q.","year":"2022","unstructured":"S. Q. Zhang, J. Lin, and Q. Zhang. 2022. A multi-agent reinforcement learning approach for efficient client selection in federated learning. In Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI\u201922)."},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3056919"},{"key":"e_1_3_1_31_2","series-title":"Proceedings of Machine Learning Research","first-page":"11492","volume-title":"Proceedings of the 37th International Conference on Machine Learning","volume":"119","author":"Zhou Dongruo","year":"2020","unstructured":"Dongruo Zhou, Lihong Li, and Quanquan Gu. 2020. Neural contextual bandits with UCB-based exploration. In Proceedings of the 37th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol. 119), Hal Daum\u00e9 III and Aarti Singh (Eds.). PMLR, 11492\u201311502."},{"key":"e_1_3_1_32_2","first-page":"11492","volume-title":"Proceedings of ICML","volume":"119","author":"Zhou D.","year":"2020","unstructured":"D. Zhou, L. Li, and Q. Gu. 2020. Neural contextual bandits with UCB-based exploration. In Proceedings of ICML, Vol. 119. 11492\u201311502."},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.07.098"}],"container-title":["ACM Transactions on Modeling and Performance Evaluation of Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3721480","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3721480","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:09:48Z","timestamp":1750295388000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3721480"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,30]]},"references-count":32,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,6,30]]}},"alternative-id":["10.1145\/3721480"],"URL":"https:\/\/doi.org\/10.1145\/3721480","relation":{},"ISSN":["2376-3639","2376-3647"],"issn-type":[{"value":"2376-3639","type":"print"},{"value":"2376-3647","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,30]]},"assertion":[{"value":"2024-05-08","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-02-10","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}