Robust aggregation algorithms for federated learning in unreliable network environments

Ziyang Zeng; Shiyu Yang; Guanyu Ding

doi:10.54097/n0dpaf43

Authors

Ziyang Zeng
Shiyu Yang
Guanyu Ding

DOI:

https://doi.org/10.54097/n0dpaf43

Keywords:

Federated Learning, Robust Aggregation, Byzantine-Resilient Algorithms, Unreliable Networks, Edge Computing

Abstract

Federated learning (FL) allows joint model training on distributed devices without losing data locality, but its results are significantly worse in unreliable network systems where packets are dropped, clients fail, resources are heterogeneous, and adversarial (Byzantine) agents exist. The viability of FL to withstand these unfavorable conditions is keyed on the robust aggregation algorithms. The paper meticulously examines powerful methods of aggregation, which include: geometric-median methods (RFA), Krum/Multi-Krum, trimmed-mean/coordinate-wise defenses, g-divergence estimators, trust-based aggregators (FLTrust), and layer-wise aggregation methods (FedRoLA) and compares their performance on simulated unreliable networks, which model packet loss, communication delay, and malicious client actions (McMahan et al., 2017; Blanchard et al., 2017; P We examine accuracy, convergence speed, communication cost and resilience in the face of model-poisoning attacks with the help of benchmark image tasks and a set of network unreliability scenarios. We find that robust aggregators combining statistical outlier resistance and structural (layer-wise) aggregation or trust calibration (especially RFA and FedRoLA) are more accurate and converge more quickly than naive FedAvg in high packet-loss and moderate Byzantine contamination and we observe up to 12 percent improvement in test accuracy with 30 percent simulated packet loss. We also talk about the trade offs between robustness, communication overhead and privacy (secure aggregation) and present a hybrid design pattern that incorporates robust aggregation and adaptive client selection with secure aggregation so as to address both unreliable links as well as adversarial updates. The results provide prescriptive advice on the use of FL in mobile, IoT, and vehicular networks that have limited reliability and security requirements and provide future directions such as privacy-conscious robust aggregation, fairness-conscious weighting, and testbed implementation.

Downloads

Download data is not yet available.

References

[1] Pillutla, K., Kakade, S. M., & Harchaoui, Z. (2022). Robust aggregation for federated learning. IEEE Transactions on Signal Processing, 70, 1142-1154. https://doi.org/10.1109/TSP.2022.3153135

[2] Zheng, Y., Lai, S., Liu, Y., Yuan, X., Yi, X., & Wang, C. (2022). Aggregation service for federated learning: An efficient, secure, and more resilient realization. IEEE Transactions on Dependable and Secure Computing, 20(2), 988-1001. https://doi.org/10.1109/TDSC.2022.3146448

[3] Ghosh, A., Hong, J., Yin, D., & Ramchandran, K. (2019). Robust federated learning in a heterogeneous environment. arXiv preprint arXiv:1906.06629. https://doi.org/10.48550/arXiv.1906.06629

[4] Moshawrab, M., Adda, M., Bouzouane, A., Ibrahim, H., & Raad, A. (2023). Reviewing federated learning aggregation algorithms: Strategies, contributions, limitations, and future perspectives. Electronics, 12(10), 2287. https://doi.org/10.3390/electronics12102287

[5] Tahmasebian, F., Lou, J., & Xiong, L. (2022, October). RobustFed: A truth inference approach for robust federated learning. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management (pp. 1868-1877). https://doi.org/10.1145/3511808.3557439

[6] Kang, J., Xiong, Z., Niyato, D., Zou, Y., Zhang, Y., & Guizani, M. (2020). Reliable federated learning for mobile networks. IEEE Wireless Communications, 27(2), 72-80. https://doi.org/10.1109/MWC.001.1900119

[7] Sharma, M., & Kaur, P. (2023). Reliable federated learning in a cloud-fog-IoT environment. Journal of Supercomputing, 79(14). https://doi.org/10.1007/s11227-023-05252-w

[8] McMahan, B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. (2017). Communication-efficient learning of deep networks from decentralized data. In Artificial Intelligence and Statistics (pp. 1273–1282). PMLR.

[9] Liu, Z., Guo, J., Yang, W., Fan, J., Lam, K. Y., & Zhao, J. (2022). Privacy-preserving aggregation in federated learning: A survey. IEEE Transactions on Big Data.

[10] Yin, D., Chen, Y., Kannan, R., & Bartlett, P. (2018). Byzantine-robust distributed learning: Towards optimal statistical rates. In International Conference on Machine Learning (pp. 5650-5659). PMLR.

[11] Zhao, L., Jiang, J., Feng, B., Wang, Q., Shen, C., & Li, Q. (2021). SEAR: Secure and efficient aggregation for Byzantine-robust federated learning. IEEE Transactions on Dependable and Secure Computing, 19(5), 3329-3342. https://doi.org/10.1109/TDSC.2021.3093711

[12] Chen, Z., Yi, W., Liu, Y., & Nallanathan, A. (2024). Robust federated learning for unreliable and resource-limited wireless networks. IEEE Transactions on Wireless Communications, 23(8), 9793-9809. https://doi.org/10.1109/TWC.2024.3366393

[13] Wang, R., Yang, L., Tang, T., Yang, B., & Wu, D. (2024). Robust federated learning for heterogeneous clients and unreliable communications. IEEE Transactions on Wireless Communications, 23(10), 13440-13455. https://doi.org/10.1109/TWC.2024.3401395

[14] Khan, N., Nisar, S., Khan, M. A., Rehman, Y. A. U., Noor, F., & Barb, G. (2025). Optimizing federated learning with aggregation strategies: A comprehensive survey. IEEE Open Journal of the Computer Society. https://doi.org/10.1109/OJCS.2025.3590102

[15] Esteves, L., Portugal, D., Peixoto, P., & Falcao, G. (2023). Towards mobile federated learning with unreliable participants and selective aggregation. Applied Sciences, 13(5), 3135. https://doi.org/10.3390/app13053135

[16] Li, Z., Zhou, Y., Wu, D., Tang, T., & Wang, R. (2022). Fairness-aware federated learning with unreliable links in resource-constrained Internet of Things. IEEE Internet of Things Journal, 9(18), 17359-17371. https://doi.org/10.1109/JIOT.2022.3156046

[17] Salehi, M., & Hossain, E. (2021). Federated learning in unreliable and resource-constrained cellular wireless networks. IEEE Transactions on Communications, 69(8), 5136-5151. https://doi.org/10.1109/TCOMM.2021.3081746

[18] Myakala, P. K., & Agrawal, M. (2025). Fault-tolerant federated learning framework for edge devices in unstable networks. Authorea Preprints. https://doi.org/10.36227/techrxiv.174612128.82578829/v1

[19] Yang, Z., Cheng, C., Li, Z., Wang, R., & Zhang, X. (2025). Reliable federated learning based on delayed gradient aggregation for intelligent connected vehicles. Engineering Applications of Artificial Intelligence, 140, 109719. https://doi.org/10.1016/j.engappai.2024.109719

[20] Ang, F., Chen, L., Zhao, N., Chen, Y., Wang, W., & Yu, F. R. (2020). Robust federated learning with noisy communication. IEEE Transactions on Communications, 68(6), 3452-3464. https://doi.org/10.1109/TCOMM.2020.2979149

[21] Li, C.-J., Huang, P.-H., Ma, Y.-T., Hung, H., & Huang, S.-Y. (2022). Robust aggregation for federated learning by minimum γ-divergence estimation. Entropy, 24(5), 686. https://doi.org/10.3390/e24050686

[22] Pillutla, K., Kakade, S. M., & Harchaoui, Z. (2022). Robust aggregation for federated learning. IEEE Transactions on Signal Processing, 70, 1142–1154. https://doi.org/10.1109/TSP.2022.3153135

[23] Miao, Y., et al. (2022). Privacy-preserving Byzantine-robust federated learning. IEEE Transactions on Information Forensics and Security. https://doi.org/10.1109/TIFS.2022.3196274

[24] Blanchard, P., El Mhamdi, E. M., Guerraoui, R., & Stainer, J. (2017). Machine learning with adversaries: Byzantine-tolerant gradient descent. NeurIPS. https://doi.org/10.5555/3294771.3294783

[25] Cao, X., Fang, M., Liu, J., & Gong, N. Z. (2021). FLTrust: Byzantine-robust federated learning via trust bootstrapping. NDSS Symposium 2021. https://doi.org/10.14722/ndss.2021.24434

[26] Ma, X., Zhou, Y., Wang, L., & Miao, M. (2022). Privacy-preserving Byzantine-robust federated learning. Computer Standards & Interfaces, article 103561. https://doi.org/10.1016/j.csi.2021.103561

[27] Shejwalkar, V., & Houmansadr, A. (2021). Manipulating the Byzantine: Optimizing model poisoning attacks and defenses in federated learning. NDSS 2021. https://doi.org/10.14722/ndss.2021.24498

[28] Zhu, B., et al. (2023). Byzantine-robust federated learning with optimal statistical guarantees. Proceedings / ML Research (PMLR). https://proceedings.mlr.press/v206/zhu23b.html

[29] Pillutla, K., Kakade, S. M., & Harchaoui, Z. (2019). Robust aggregation for federated learning. https://doi.org/10.1109/TSP.2022.3153135

[30] Yan, G., Wang, H., & Yuan, X. (2024). FedRoLA: Robust federated learning against model poisoning via layer-based aggregation. KDD 2024. https://doi.org/10.1145/3637528.3671906