Abstract
The rapid growth of the Internet of Things (IoT) and the adoption of edge computing have intensified the need for real-time intelligent services that also protect user privacy. Conventional cloud-centric learning pipelines and synchronous federated learning (FL) protocols (e.g., FedAvg) often fail to meet strict latency requirements in heterogeneous networks due to straggler effects and global synchronization delays. This paper proposes a novel FL architecture tailored to latency-sensitive edge environments that combines non-blocking asynchronous aggregation with explicit privacy preservation. The core contribution is an asynchronous streaming aggregation protocol equipped with an adaptive damping function that reduces the adverse impact of stale client updates and sustains convergence without reverting to strict synchronization. To improve stability under Non-IID data distributions, the server maintains a global momentum buffer that smooths stochastic fluctuations across client updates. Communication overhead is further reduced through sparse Top-k compression with error-feedback accumulation, enabling frequent transmission of the most informative gradient components while limiting accuracy degradation. Privacy is ensured via local differential privacy (LDP) using gradient clipping and additive Gaussian noise, while privacy loss accounting is performed with Rényi Differential Privacy (RDP), providing tighter composition bounds and better alignment with continuous asynchronous updates. A theoretical analysis establishes convergence with bounded excess risk for convex objectives, supporting the practical feasibility of high-performance, privacy-preserving Edge AI. The paper also highlights remaining challenges – including non-convex optimization in deep models, robustness against poisoning/Byzantine behaviors, and extreme network instability—and outlines directions for future work.
References
Abadi, M., Chu, A., Goodfellow, I., McMahan, H. B., Mironov, I., Talwar, K., & Zhang, L. (2016). Deep learning with differential privacy. In Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security (pp. 308–318). https://doi.org/10.1145/2976749.2978318
Aji, A. F., & Heafield, K. (2017). Sparse communication for distributed gradient descent. In M. Palmer, R. Hwa, & S. Riedel (Eds.), Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (pp. 440–445). Association for Computational Linguistics. https://doi.org/10.18653/v1/D17-1045
Chen, M., Mao, B., & Ma, T. (2021). FedSA: A staleness-aware asynchronous federated learning algorithm with non-IID data. Future Generation Computer Systems, (120), 1–12. https://doi.org/10.1016/j.future.2021.02.012
Chen, M., Yang, Z., Saad, W., Yin, C., Poor, H. V., & Cui, S. (2021). A joint learning and communications framework for federated learning over wireless networks. IEEE Transactions on Wireless Communications, 20(1), 269–283. https://doi.org/10.1109/TWC.2020.3024629
Kairouz, P., & McMahan, H. B. (2021). Advances and open problems in federated learning. Foundations and Trends in Machine Learning, 14(1–2), 1–210. https://doi.org/10.1561/2200000083
Khan, L. U., Saad, W., Han, Z., & Hong, C. S. (2020). Dispersed federated learning: Vision, taxonomy, and future directions (arXiv:2008.05189). arXiv. https://doi.org/10.48550/arXiv.2008.0518
Li, T., Sahu, A. K., Talwalkar, A., & Smith, V. (2020). Federated learning: Challenges, methods, and future directions. IEEE Signal Processing Magazine, 37(3), 50–60. https://doi.org/10.1109/MSP.2020.2975749
Li, Y., Zhou, Y., Jolfaei, A., Yu, D., Xu, G., & Zheng, X. (2021). Privacy-preserving federated learning framework based on chained secure multiparty computing. IEEE Internet of Things Journal, 8(8), 6178–6186. https://doi.org/10.1109/JIOT.2020.3022911
McMahan, H. B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. (2016). Communication-Efficient Learning of Deep Networks from Decentralized Data. International Conference on Artificial Intelligence and Statistics. https://www.semanticscholar.org/paper/Communication-Efficient-Learning-of-Deep-Networks-McMahan-Moore/d1dbf643447405984eeef098b1b320dee0b3b8a7
Mironov, I. (2017). Rényi differential privacy. In 2017 IEEE 30th Computer Security Foundations Symposium (CSF) (pp. 263–275). IEEE. https://doi.org/10.1109/CSF.2017.11
Shi, W., Cao, J., Zhang, Q., Li, Y., & Xu, L. (2016). Edge computing: Vision and challenges. IEEE Internet of Things Journal, 3(5), 637–646. https://doi.org/10.1109/JIOT.2016.2579198
Sprague, M. R., Jalalirad, A., Scavuzzo, M., Capota, C., Neun, M., Do, L., & Kopp, M. (2019). Asynchronous federated learning for geospatial applications. In A. Monreale et al. (Eds.), Machine learning and knowledge discovery in databases: ECML PKDD 2018 workshops (Communications in Computer and Information Science, Vol. 967, pp. 21–28). Springer. https://doi.org/10.1007/978-3-030-14880-5_2
Tan, Y., Long, G., LIU, L., Zhou, T., Lu, Q., Jiang, J., & Zhang, C. (2022). FedProto: Federated Prototype Learning across Heterogeneous Clients. Proceedings of the AAAI Conference on Artificial Intelligence, 36(8), 8432–8440. https://doi.org/10.1609/aaai.v36i8.20819
Wang, J., Liu, Q., Liang, H., Joshi, G., & Poor, H. V. (2020). Tackling the objective inconsistency problem in heterogeneous federated optimization. Advances in Neural Information Processing Systems, (33), 7611-7623. https://collaborate.princeton.edu/en/publications/tackling-the-objective-inconsistency-problem-in-heterogeneous-fed/
Wei, K., Li, J., Ding, M., Ma, C., Yang, H. H., Farokhi, F., Jin, S., & Poor, H. V. (2020). Federated learning with differential privacy: Algorithms and performance analysis. IEEE Transactions on Information Forensics and Security, (15), 3454–3469. https://doi.org/10.1109/TIFS.2020.2988575
Xie, C., Koyejo, S., & Gupta, I. (2019). Asynchronous federated optimization (arXiv:1903.03934). arXiv. https://doi.org/10.48550/arXiv.1903.03934
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Copyright (c) 2026 Klymenko Serhii