Enhancing Communication Efficiency in Federated Learning Through Client Contribution Selection Based Normalized L2 Norm with Cosine Similarity and L2 Norm Filtering
Article Sidebar
Main Article Content
Abstract
Federated Learning (FL) is a decentralized machine learning framework in which clients train models locally and share only their updates with a central server for aggregation. However, FL faces critical communication efficiency and scalability challenges, particularly in large-scale networks where high communication overhead and slow convergence impede deployment. This paper proposes a novel client contribution selection strategy that combines Cosine Similarity and L2 Norm Filtering (CLF-C) with a Normalized L2-Based Client Selection (NLCS) mechanism to enhance communication efficiency and model convergence. The proposed approach prioritizes client updates that are both significant in magnitude and directionally aligned with the global model, thereby reducing unnecessary participation and improving aggregation quality. Experimental evaluations on the MNIST dataset demonstrate that the proposed method achieves 96.8% accuracy in 68 communication rounds using 468 clients, outperforming baseline models such as FedAvg (96.5%, 80 rounds, 800 clients) and FedProx (96.3%, 90 rounds, 900 clients). In addition to reducing communication rounds, the method enhances model robustness by filtering out misaligned or potentially adversarial clients. Importantly, it introduces no additional computational overhead for clients, making it well-suited for resource-constrained environments. This work contributes a scalable and secure solution for improving the efficiency of Federated Learning without compromising model performance.
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Journal of Studies in Science and Engineering is licensed under a Creative Commons Attribution License 4.0 (CC BY-4.0).
References
G. S. Nariman and H. K. Hamarashid, "Hierarchical federated learning for health trend prediction and anomaly detection using pharmacy data: from zone to national scale," International Journal of Data Science and Analytics, pp:1-20, 2025, doi: 10.1007/s41060-025-00756-5.
S. Jiang, Y. Li, F. Firouzi, and K. Chakrabarty, "Federated clustered multi-domain learning for health monitoring," Scientific Reports, vol. 14, no. 1, p. 903, 2024, doi: 10.1038/s41598-024-51344-9.
M. Asad and S. Otoum, "Bppfl: a blockchain-based framework for privacy-preserving federated learning," Cluster Computing, vol. 28, no. 2, p. 126, 2024, doi: 10.1007/s10586-024-04834-4.
C. Ma, X. Li, B. Huang, G. Li, and F. Li, "Personalized client-edge-cloud hierarchical federated learning in mobile edge computing," Journal of Cloud Computing, vol. 13, no. 1, p. 161, 2024, doi: 10.1186/s13677-024-00721-w.
J. Li, M. Lu, J. Zhang, and J. Wu, "Aldp-fl: an adaptive local differential privacy-based federated learning mechanism for IoT," International Journal of Information Security, vol. 24, no. 1, p. 23, 2024, doi: 10.1007/s10207-024-00933-w.
J. Wen, Z. Zhang, Y. Lan, Z. Cui, J. Cai, and W. Zhang, "A survey on federated learning: challenges and applications," International Journal of Machine Learning and Cybernetics, vol. 14, no. 2, pp. 513-535, 2023/02/01 2023, doi: 10.1007/s13042-022-01647-y.
S. Ji et al., "Emerging trends in federated learning: from model fusion to federated X learning," International Journal of Machine Learning and Cybernetics, vol. 15, no. 9, pp. 3769-3790, 2024, doi: 10.1007/s13042-024-02119-1.
J. Xu, X. Li, K. Zhu, L. Zhou, and Y. Zhao, "Two-stage model fusion scheme based on knowledge distillation for stragglers in federated learning," International Journal of Machine Learning and Cybernetics, vol. 16, pp: 3067–3083 2024, doi: 10.1007/s13042-024-02436-5.
S. D N, A. B, and S. Ambesange, "Smart client selection strategies for enhanced federated learning in digital healthcare applications," Multimedia Tools and Applications, pp:1-16, 2024, doi: 10.1007/s11042-024-19403-5.
Y. Liu, H. Xia, W. Li, and T. Niu, "Mitigating bias in heterogeneous federated learning via stratified client selection," Peer-to-Peer Networking and Applications, vol. 18, no. 2, p. 11, 2025, doi: 10.1007/s12083-024-01886-6.
L. Hu, Y. Hu, L. Jiang, and W. Long, "Federated learning client selection algorithm based on gradient similarity," Cluster Computing, vol. 28, no. 2, p. 134, 2024, doi: 10.1007/s10586-024-04846-0.
G. S. Nariman and H. K. Hamarashid, "Communication overhead reduction in federated learning: a review," International Journal of Data Science and Analytics, vol. 19, pp: 185–216, 2024, doi: 10.1007/s41060-024-00691-x.
B. Soudan, S. Abbas, A. Kubba, O. Abu Waraga, M. Abu Talib, and Q. Nasir, "Scalability and performance evaluation of federated learning frameworks: a comparative analysis," International Journal of Machine Learning and Cybernetics, vol. 16, pp: 3329–3343 2025, doi: 10.1007/s13042-024-02453-4.
H. Wu and P. Wang, "Node Selection Toward Faster Convergence for Federated Learning on Non-IID Data," IEEE Transactions on Network Science and Engineering, vol. 9, no. 5, pp. 3099-3111, 2022, doi: 10.1109/TNSE.2022.3146399.
Y. J. Cho, J. Wang, and G. Joshi, "Client selection in federated learning: Convergence analysis and power-of-choice selection strategies," arXiv preprint arXiv:2010.01243, 2020.
M. Duan et al., "FedGroup: Efficient Federated Learning via Decomposed Similarity-Based Clustering," in 2021 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/SocialCom/SustainCom), 30 Sept.-3 Oct. 2021 2021, pp. 228-237, doi: 10.1109/ISPA-BDCloud-SocialCom-SustainCom52081.2021.00042.
L. Yu, W. Nie, L. Xin, and M. Guo, "Clustered federated learning based on data distribution," in Proceedings of the 3rd International Conference on Advanced Information Science and System, 2021, pp. 1-5.
W. Chen, S. Horvath, and P. Richtarik, "Optimal client sampling for federated learning," arXiv preprint arXiv:2010.13723, 2020.
A. Cheng, P. Wang, X. S. Zhang, and J. Cheng, "Differentially private federated learning with local regularization and sparsification," in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2022, pp. 10122-10131.
P. Uthansakul, P. Anchuen, M. Uthansakul, and A. A. Khan, "Estimating and Synthesizing QoE Based on QoS Measurement for Improving Multimedia Services on Cellular Networks Using ANN Method," IEEE Transactions on Network and Service Management, vol. 17, no. 1, pp. 389-402, 2020, doi: 10.1109/TNSM.2019.2946091.
P. Uthansakul, P. Anchuen, M. Uthansakul, and A. A. Khan, "QoE-aware self-tuning of service priority factor for resource allocation optimization in LTE networks," IEEE Transactions on Vehicular Technology, vol. 69, no. 1, pp. 887-900, 2019.
A. A. Khan, M. Driss, W. Boulila, G. A. Sampedro, S. Abbas, and C. Wechtaisong, "Privacy Preserved and Decentralized Smartphone Recommendation System," IEEE Transactions on Consumer Electronics, vol. 70, no. 1, pp. 4617-4624, 2024, doi: 10.1109/TCE.2023.3323406.
A. I. Kawoosa, D. Prashar, M. Faheem, N. Jha, and A. A. Khan, "Using machine learning ensemble method for detection of energy theft in smart meters," IET Generation, Transmission & Distribution, vol. 17, no. 21, pp. 4794-4809, 2023.
L. Deng, "The mnist database of handwritten digit images for machine learning research [best of the web]," IEEE signal processing magazine, vol. 29, no. 6, pp. 141-142, 2012.
B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. A. y Arcas, "Communication-efficient learning of deep networks from decentralized data," in Artificial intelligence and statistics, 2017: PMLR, pp. 1273-1282.
C. Briggs, Z. Fan, and P. Andras, "Federated learning with hierarchical clustering of local updates to improve training on non-IID data," in 2020 International Joint Conference on Neural Networks (IJCNN), 2020: IEEE, pp. 1-9.
Goran1984. "Enhancing-Communication-Efficiency-in-FL." GitHub. https://github.com/Goran1984/Enhancing-Communication-Efficiency-in-FL-/blob/dc90beb41adb46c78b14e9a18cbca08eec9dacc9/Main-1 (accessed Feb 28, 2025, 2025).
M. Fang, X. Cao, J. Jia, and N. Gong, "Local model poisoning attacks to {Byzantine-Robust} federated learning," in 29th USENIX security symposium (USENIX Security 20), 2020, pp. 1605-1622.
L. Lyu et al., "Privacy and Robustness in Federated Learning: Attacks and Defenses," IEEE Transactions on Neural Networks and Learning Systems, vol. 35, no. 7, pp. 8726-8746, 2024, doi: 10.1109/TNNLS.2022.3216981.
G. Baruch, M. Baruch, and Y. Goldberg, "A little is enough: Circumventing defenses for distributed learning," Advances in Neural Information Processing Systems, vol. 32, pp:1-11, 2019.
E. Bagdasaryan, A. Veit, Y. Hua, D. Estrin, and V. Shmatikov, "How to backdoor federated learning," in International conference on artificial intelligence and statistics, 2020: PMLR, pp. 2938-2948.
M. Ribero and H. Vikalo, "Reducing communication in federated learning via efficient client sampling," Pattern Recognition, vol. 148, p. 110122, 2024.
J. Wolfrath, N. Sreekumar, D. Kumar, Y. Wang, and A. Chandra, "Haccs: Heterogeneity-aware clustered client selection for accelerated federated learning," in 2022 IEEE international parallel and distributed processing symposium (IPDPS), 2022: IEEE, pp. 985-995.
Z. Li et al., "Data heterogeneity-robust federated learning via group client selection in industrial IoT," IEEE Internet of Things Journal, vol. 9, no. 18, pp. 17844-17857, 2022.
A. Albaseer, M. Abdallah, A. Al-Fuqaha, and A. Erbad, "Client selection approach in support of clustered federated learning over wireless edge networks," in 2021 IEEE global communications conference (GLOBECOM), 2021: IEEE, pp. 1-6.
B. Wu, F. Fang, and X. Wang, "Joint Age-Based Client Selection and Resource Allocation for Communication-Efficient Federated Learning Over NOMA Networks," IEEE Transactions on Communications, vol. 72, no. 1, pp. 179-192, 2024, doi: 10.1109/TCOMM.2023.3317300.
T. Huang, W. Lin, L. Shen, K. Li, and A. Y. Zomaya, "Stochastic Client Selection for Federated Learning With Volatile Clients," IEEE Internet of Things Journal, vol. 9, no. 20, pp. 20055-20070, 2022, doi: 10.1109/JIOT.2022.3172113.
A. E. W. Johnson et al., "MIMIC-III, a freely accessible critical care database," Scientific Data, vol. 3, no. 1, p. 160035, 2016/05/24 2016, doi: 10.1038/sdata.2016.35.