Adaptive Local Step Tuning for federated learning under data heterogeneity
Tóm tắt: 27
| 
PDF: 11 
##plugins.themes.academic_pro.article.main##
Author
Từ khóa:
Federated Learning
Non-IID Data
Client Drift
Adaptive Local Step Tuning
Tóm tắt
Federated Learning (FL) enables collaborative model training across decentralized clients while preserving data privacy. However, non-IID data often induces client drift and unstable convergence due to mismatched local training dynamics across clients. Standard FL methods typically utilize fixed local training budgets, leading to computational inefficiency in heterogeneous environments. This paper proposes Adaptive Local Step Tuning (ALST), a lightweight client-autonomous framework that dynamically adjusts local training steps based on an empirical drift proxy estimated from a single probe update. The framework operates entirely on the client side without introducing additional communication overhead or metadata sharing. Experimental results on EMNIST and CIFAR-100 demonstrate that ALST maintains stable convergence while improving the efficiency-performance trade-off under heterogeneous settings. While EMNIST validates the stability of the proposed adaptive mechanism, results on the more challenging CIFAR-100 benchmark show that ALST reduces total local computation by 23.09% while maintaining predictive performance within 0.14% of fixed-work baselines.
Tài liệu tham khảo
-
[1] B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. A. y Arcas, “Communication-Efficient Learning of Deep Networks from Decentralized Data,” in Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, Fort Lauderdale, FL, USA, PMLR, 2017, pp. 1273–1282.
[2] P. Kairouz et al., “Advances and Open Problems in Federated Learning,” Foundations and Trends in Machine Learning, vol. 14, no. 1–2, pp. 1–210, Jun. 2021. https://doi.org/10.1561/2200000083
[3] D. M. J. Gutierrez et al., “Non-IID Data in Federated Learning: A Survey with Taxonomy, Metrics, Methods, Frameworks and Future Directions,” arXiv preprint, arXiv:2411.12377, 2024. [Online]. Available: https://arxiv.org/abs/2411.12377 [Accessed May 28, 2026].
[4] Q. N. Pham and D. K. Ninh, “Lightweight fall detection on edge devices via knowledge distillation,” The University of Danang - Journal of Science and Technology, vol. 23, no. 9D, pp. 74–78, Sep. 2025. https://doi.org/10.31130/ud-jst.2025.23(9D).568E
[5] X. Li, K. Huang, W. Yang, S. Wang, and Z. Zhang, “On the Convergence of FedAvg on Non-IID Data,” in Proceedings of the International Conference on Learning Representations (ICLR), 2020.
[6] M. Sherkati, W. Shi, and M. Amini, “A comprehensive evaluation of metrics on their ability to capture the degrees of Non-IIDness with label skew in federated learning,” Computers and Electrical Engineering, vol. 129, p. 110743, 2026. https://doi.org/10.1016/j.compeleceng.2025.110743
[7] H. Zhu, J. Xu, S. Liu, and Y. Jin, “Federated learning on non-IID data: A survey,” Neurocomputing, vol. 465, pp. 371–390, Nov. 2021. https://doi.org/10.1016/j.neucom.2021.07.098
[8] M. Ye, X. Fang, B. Du, P. C. Yuen, and D. Tao, “Heterogeneous Federated Learning: State-of-the-art and Research Challenges,” ACM Computing Surveys, vol. 56, no. 3, Oct. 2023. https://doi.org/10.1145/3625558
[9] S. P. Karimireddy, S. Kale, M. Mohri, S. J. Reddi, S. U. Stich, and A. T. Suresh, “SCAFFOLD: Stochastic Controlled Averaging for Federated Learning,” in Proceedings of the 37th International Conference on Machine Learning, Virtual, PMLR, 2020, pp. 5132–5143.
[10] J. Wang, Q. Liu, H. Liang, G. Joshi, and H. V. Poor, “Tackling the objective inconsistency problem in heterogeneous federated optimization,” in Proceedings of the 34th International Conference on Neural Information Processing Systems, Virtual, Curran Associates, Inc., 2020, pp. 7611–7623.
[11] T. Li, A. K. Sahu, M. Zaheer, M. Sanjabi, A. Talwalkar, and V. Smith, “Federated Optimization in Heterogeneous Networks,” in Proceedings of Machine Learning and Systems, vol. 2, pp. 429–450, 2020.
[12] S. Wang et al., “Adaptive Federated Learning in Resource Constrained Edge Computing Systems,” IEEE Journal on Selected Areas in Communications, vol. 37, no. 6, pp. 1205–1221, Jun. 2019. https://doi.org/10.1109/JSAC.2019.2904348
[13] J. Wang and G. Joshi, “Adaptive Communication Strategies to Achieve the Best Error-Runtime Trade-off in Local-Update SGD,” in Proceedings of Machine Learning and Systems, vol. 1, pp. 212–229, 2019.
[14] K. Hsieh, A. Phanishayee, O. Mutlu, and P. Gibbons, “The non-IID data quagmire of decentralized machine learning,” in Proceedings of the 37th International Conference on Machine Learning, Virtual, PMLR, 2020, pp. 4387–4398.
[15] S. Reddi et al., “Adaptive Federated Optimization,” in Proceedings of the International Conference on Learning Representations (ICLR), 2021.
[16] The TensorFlow Federated Authors, “TensorFlow Federated: Machine Learning on Decentralized Data,” TensorFlow.org. [Online]. Available: https://www.tensorflow.org/federated [Accessed May 28, 2026].
Xem thêm
##plugins.themes.academic_pro.article.sidebar##
Đã Xuất bản
Sep 30, 2026
Download
Cách trích dẫn
Loc, H. T. “Adaptive Local Step Tuning for Federated Learning under Data Heterogeneity”. Tạp Chí Khoa học Và Công nghệ Đại học Đà Nẵng, vol 24, số p.h 9, Tháng Chín 2026, tr 90-95, doi:10.31130/ud-jst.2026.24(9).369E.
