A Robust Client Selection Mechanism for Federated Learning Environments
DOI:
https://doi.org/10.5753/jbcs.2024.4325Keywords:
Federated Learning, Client Selection, EntropyAbstract
There is a exponential growth of data usage, specially due to the proliferation of connected applications with personalized models for different applications. In this context, Federated Learning (FL) emerges as a promising solution to enable collaborative model training while preserving the privacy and autonomy of participating clients. In a typical FL scenario, clients exhibit significant heterogeneity in terms of data distribution and hardware configurations. In this way, randomly sampling clients in each training round may not fully exploit the local updates from heterogeneous clients, resulting in lower model accuracy, slower convergence rate, degraded fairness, etc. In addition, malicious users could disseminate incorrect weights, which may decrease the accuracy of aggregated models and increase the time for convergence in FL. In this article, we introduce Resilience-aware Client Selection Mechanism for non-IID data and malicious clients in FL environment, called RICA. The proposed mechanism employs data size and entropy as criteria for client selection. In addition, RICA relies Centroid-Based Kernel Alignment (CKA) to identify and exclude potentially malicious clients. Our evaluation shows an improvement of 125% in Accuracy values in a scenario of malicious clients, which means the RICA+CKA demonstrates a more stable and resilient approach, reaching 90% accuracy in a few rounds compared to the default average approach, reached only around 30%. Therefore, results of the behavior of RICA+CKA in different datasets show the evaluation of different numbers of clients reaching around 90% while the other approach does not pass the 50% Accuracy.
Downloads
References
Albaseer, A., Abdallah, M., Al-Fuqaha, A., and Erbad, A. (2021). Client Selection Approach in Support of Clustered Federated Learning over Wireless Edge Networks. 2021 IEEE Global Communications Conference, GLOBECOM 2021 - Proceedings. DOI: 10.1109/GLOBECOM46510.2021.9685938.
Barros, A., Rosário, D., Cerqueira, E., and da Fonseca, N. L. (2021). A strategy to the reduction of communication overhead and overfitting in federated learning. In Anais do XXVI Workshop de Gerência e Operação de Redes e Serviços, pages 1-13. SBC. DOI: 10.5753/wgrs.2021.17181.
Fu, L., Zhang, H., Gao, G., Zhang, M., and Liu, X. (2023). Client Selection in Federated Learning: Principles, Challenges, and Opportunities. IEEE Internet of Things Journal, 10(24):21811-21819.
Ghodsi, Z., Javaheripi, M., Sheybani, N., Zhang, X., Huang, K., and Koushanfar, F. (2023). zprobe: Zero peek robustness checks for federated learning. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 4860-4870. Available online [link].
Ghosh, A., Chung, J., Yin, D., and Ramchandran, K. (2022). An efficient framework for clustered federated learning. IEEE Transactions on Information Theory, 68(12):8076-8091. Available online [link].
Jee Cho, Y., Wang, J., and Joshi, G. (2022). Towards understanding biased client selection in federated learning. In Camps-Valls, G., Ruiz, F. J. R., and Valera, I., editors, Proceedings of The 25th International Conference on Artificial Intelligence and Statistics, volume 151 of Proceedings of Machine Learning Research, pages 10351-10375. PMLR. Available online [link].
Kusano, K. D., Scanlon, J. M., Chen, Y.-H., McMurry, T. L., Chen, R., Gode, T., and Victor, T. (2023). Comparison of waymo rider-only crash data to human benchmarks at 7.1 million miles.
Le, J., Zhang, D., Lei, X., Jiao, L., Zeng, K., and Liao, X. (2023). Privacy-preserving federated learning with malicious clients and honest-but-curious servers. IEEE Transactions on Information Forensics and Security. DOI: 10.1109/TIFS.2023.3295949.
Li, Q., He, B., and Song, D. (2021). Model-contrastive federated learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 10713-10722. Available online [link].
Liu, Y., Yu, J. J., Kang, J., Niyato, D., and Zhang, S. (2020). Privacy-Preserving Traffic Flow Prediction: A Federated Learning Approach. IEEE Internet of Things Journal, 7(8):7751-7763. DOI: 10.1109/JIOT.2020.2991401.
Lobato, W., Costa, J. B., Souza, A. M., Rosario, D., Sommer, C., and Villas, L. A. (2022). FLEXE: Investigating Federated Learning in Connected Autonomous Vehicle Simulations. IEEE Vehicular Technology Conference, 2022-Septe. DOI: 10.1109/VTC2022-Fall57202.2022.10012905.
Ma, X., Zhu, J., Lin, Z., Chen, S., and Qin, Y. (2022). A state-of-the-art survey on solving non-iid data in federated learning. Future Generation Computer Systems, 135:244-258. DOI: 10.1016/j.future.2022.05.003.
McMahan, H. B., Moore, E., Ramage, D., Hampson, S., and y Arcas, B. A. (2017). Communication-efficient learning of deep networks from decentralized data. Available online [link].
Orlandi, F. C., Dos Anjos, J. C., Santana, J. F. d. P., Leithardt, V. R., and Geyer, C. F. (2023). Entropy to mitigate non-iid data problem on federated learning for the edge intelligence environment. IEEE Access. DOI: 10.1109/ACCESS.2023.3298704.
Raghu, M., Unterthiner, T., Kornblith, S., Zhang, C., and Dosovitskiy, A. (2021). Do vision transformers see like convolutional neural networks? Advances in Neural Information Processing Systems, 34:12116-12128. Available online [link].
Sattler, F., Müller, K.-R., Wiegand, T., and Samek, W. (2020). On the byzantine robustness of clustered federated learning. In ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 8861-8865. IEEE. DOI: 10.1109/ICASSP40776.2020.9054676.
Smestad, C. and Li, J. (2023). A systematic literature review on client selection in federated learning. In Proceedings of the 27th International Conference on Evaluation and Assessment in Software Engineering, EASE '23, page 2–11, New York, NY, USA. Association for Computing Machinery. DOI: 10.1145/3593434.3593438.
Song, R., Zhou, L., Lakshminarasimhan, V., Festag, A., and Knoll, A. (2022). Federated Learning Framework Coping with Hierarchical Heterogeneity in Cooperative ITS. In IEEE 25th International Conference on Intelligent Transportation Systems (ITSC). IEEE. DOI: 10.1109/ITSC55140.2022.9922064.
Sousa, J. L. R., Lobato, W., Rosário, D., Cerqueira, E., and Villas, L. A. (2023). Entropy-based client selection mechanism for vehicular federated environments. In Proceedings of the 22nd Workshop on Performance of Computer and Communication Systems (WPERFORMANCE), pages 37-48. SBC. DOI: 10.5753/wperformance.2023.230700.
Souza, A., Bittencourt, L., Cerqueira, E., Loureiro, A., and Villas, L. (2023). Dispositivos, eu escolho vocês: Seleção de clientes adaptativa para comunicação eficiente em aprendizado federado. In Anais do XLI Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos, pages 1-14, Porto Alegre, RS, Brasil. SBC. DOI: 10.5753/sbrc.2023.499.
Xiong, Y., Wang, R., Cheng, M., Yu, F., and Hsieh, C.-J. (2023). Feddm: Iterative distribution matching for communication-efficient federated learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 16323-16332. Available online [link].
Yan, G., Wang, H., Yuan, X., and Li, J. (2023). Defl: defending against model poisoning attacks in federated learning via critical learning periods awareness. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 37, pages 10711-10719. DOI: 10.1609/aaai.v37i9.26271.
Zhang, J., Hua, Y., Wang, H., Song, T., Xue, Z., Ma, R., and Guan, H. (2023a). Fedala: Adaptive local aggregation for personalized federated learning. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 37, pages 11237-11244. DOI: 10.1609/aaai.v37i9.26330.
Zhang, X., Liu, J., Hu, T., Chang, Z., Zhang, Y., and Min, G. (2023b). Federated learning-assisted vehicular edge computing: Architecture and research directions. IEEE Vehicular Technology Magazine, pages 2-11. DOI: 10.1109/MVT.2023.3297793.
Zhang, Z., Cao, X., Jia, J., and Gong, N. Z. (2022). FLDetector: Defending Federated Learning Against Model Poisoning Attacks via Detecting Malicious Clients. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 2545-2555. DOI: 10.1145/3534678.3539231.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Rafael Veiga, John Sousa, Renan Morais, Lucas Bastos, Wellington Lobato, Denis Rosário, Eduardo Cerqueira
This work is licensed under a Creative Commons Attribution 4.0 International License.
