Abstract
Federated learning (FL) enables distributed clients to collaboratively train a machine learning model without sharing raw data with each other. However, it suffers from the leakage of private information from uploading models. In addition, as the model size grows, the training latency increases due to the limited transmission bandwidth and model performance degradation while using differential privacy (DP) protection. In this paper, we propose a gradient sparsification empowered FL framework with DP over wireless channels, to improve training efficiency without sacrificing convergence performance. Specifically, we first design a random sparsification algorithm to retain a fraction of the gradient elements in each client’s local model, thereby mitigating the performance degradation induced by DP and reducing the number of transmission parameters over wireless channels. Then, we analyze the convergence bound of the proposed algorithm, by modeling a non-convex FL problem. Next, we formulate a time-sequential stochastic optimization problem for minimizing the developed convergence bound, under the constraints of transmit power, the average transmitting delay, as well as the client’s DP requirement. Utilizing the Lyapunov drift-plus-penalty framework, we develop an analytical solution to the optimization problem. Extensive experiments have been implemented on three real-life datasets to demonstrate the effectiveness of our proposed algorithm. We show that our proposed algorithms can fully exploit the interworking between communication and computation to outperform the baselines, i.e., random scheduling, round robin, and delay-minimization algorithms.
References
Nguyen D C, Cheng P, Ding M, et al. Enabling AI in future wireless networks: a data life cycle perspective. IEEE Commun Surv Tutorials, 2021, 23: 553–595
Kairouz P, McMahan H B, Avent B, et al. Advances and open problems in federated learning. FNT Machine Learn, 2021, 14: 1–210
Li J, Shao Y, Wei K, et al. Blockchain assisted decentralized federated learning (BLADE-FL): performance analysis and resource allocation. IEEE Trans Parallel Distrib Syst, 2021, 33: 2401–2415
**a W, Quek T Q S, Guo K, et al. Multi-armed bandit-based client scheduling for federated learning. IEEE Trans Wireless Commun, 2020, 19: 7108–7123
Yang H H, Liu Z, Quek T Q S, et al. Scheduling policies for federated learning in wireless networks. IEEE Trans Commun, 2020, 68: 317–333
Wang S, Tuor T, Salonidis T, et al. Adaptive federated learning in resource constrained edge computing systems. IEEE J Sel Areas Commun, 2019, 37: 1205–1221
Chen M, Poor H V, Saad W, et al. Convergence time optimization for federated learning over wireless networks. IEEE Trans Wireless Commun, 2021, 20: 2457–2471
Yang Z, Chen M, Saad W, et al. Energy efficient federated learning over wireless communication networks. IEEE Trans Wireless Commun, 2021, 20: 1935–1949
Deng X, Li J, Ma C, et al. Blockchain assisted federated learning over wireless channels: dynamic resource allocation and client scheduling. IEEE Trans Wireless Commun, 2022, 22: 3537–3553
Mocanu D C, Mocanu E, Stone P, et al. Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science. Nat Commun, 2018, 9: 2383
Jiang J, Fu F, Yang T, et al. SketchML: accelerating distributed machine learning with data sketches. In: Proceedings of International Conference on Management of Data, Houston, 2018. 1269–1284
Zheng S, Shen C, Chen X. Design and analysis of uplink and downlink communications for federated learning. IEEE J Sel Areas Commun, 2021, 39: 2150–2167
Wang Y, Xu Y, Shi Q, et al. Quantized federated learning under transmission delay and outage constraints. IEEE J Sel Areas Commun, 2022, 40: 323–341
Liu S, Yu G, Yin R, et al. Joint model pruning and device selection for communication-efficient federated edge learning. IEEE Trans Commun, 2022, 70: 231–244
Wang Z, Song M, Zhang Z, et al. Beyond inferring class representatives: user-level privacy leakage from federated learning. In: Proceedings of IEEE International Conference on Computer Communications, Paris, 2019. 2512–2520
Dwork C, Roth A. The algorithmic foundations of differential privacy. FNT Theor Comput Sci, 2014, 9: 211–407
Wei K, Li J, Ding M, et al. Federated learning with differential privacy: algorithms and performance analysis. IEEE Trans Inform Forensic Secur, 2020, 15: 3454–3469
Martin A, Andy C, Ian G, et al. Deep learning with differential privacy. In: Proceedings of ACM Conference on Computer and Communications Security, Vienna, 2016. 308–318
Zhou Y, Wu S, Banerjee A. Bypassing the ambient dimension: private SGD with gradient subspace identification. In: Proceedings of International Conference on Learning Representations, Virtual, 2021
Wei K, Li J, Ma C, et al. Low-latency federated learning over wireless channels with differential privacy. IEEE J Sel Areas Commun, 2020, 40: 290–307
Mironov I, Talwar K, Zhang L. Rényi differential privacy of the sampled Gaussian mechanism. 2019. Ar**v:1908.10530
Yousefpour A, Shilov I, Sablayrolles A, et al. Opacus: user-friendly differential privacy library in PyTorch. In: Proceedings of Privacy in Machine Learning Workshop, NeurIPS, Virtual, 2021
Stich S U, Cordonnier J, Jaggi M. Sparsified SGD with memory. In: Proceedings of Advances in Neural Information Processing Systems, Montreal, 2018, 4452–4463
Dinh C T, Tran N H, Nguyen M N H, et al. Federated learning over wireless networks: convergence analysis and resource allocation. IEEE ACM Trans Networking, 2021, 29: 398–409
Zhou X, Deng Y, **a H, et al. Time-triggered federated learning over wireless networks. IEEE Trans Wireless Commun, 2022, 21: 11066–11079
You C, Feng D, Guo K, et al. Semi-synchronous personalized federated learning over mobile edge networks. IEEE Trans Wireless Commun, 2023, 22: 2262–2277
** bias reduction. In: Proceedings of IEEE Symposium on Security and Privacy, San Francisco, 2023. 2170–2189
Huang T, Lin W, Wu W, et al. An efficiency-boosting client selection scheme for federated learning with fairness guarantee. IEEE Trans Parallel Distrib Syst, 2021, 32: 1552–1564
Molchanov P, Mallya A, Tyree S, et al. Importance estimation for neural network pruning. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, 2019. 11264–11272
Neely M J. Stochastic Network Optimization with Application to Communication and Queueing Systems. Cham: Springer, 2010
Deng X, Li J, Ma C, et al. Low-latency federated learning with DNN partition in distributed industrial IoT networks. IEEE J Sel Areas Commun, 2022, 41: 755–775
Mahdian M, Yan Q. Online bipartite matching with random arrivals: an approach based on strongly factor-revealing LPs. In: Proceedings of ACM Symposium on Theory of Computing, San Jose, 2011. 597–606
LeCun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition. Proc IEEE, 1998, 86: 2278–2324
**ao H, Rasul K, Vollgraf R. Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms. 2017. Ar**v:1708.07747
Krizhevsky A, Hinton G. Learning multiple layers of features from tiny images. Dissertation for Master’s Degree. Toronto: University of Toronto, 2009
Chen M, Shlezinger N, Poor H V, et al. Communication-efficient federated learning. Proc Natl Acad Sci USA, 2021, 118: e2024789118
Yurochkin M, Agarwal M, Ghosh S, et al. Bayesian nonparametric federated learning of neural networks. In: Proceedings of International Conference on Machine Learning, 2019. 7252–7261
Liu J, Lou J, **ong L, et al. Projected federated averaging with heterogeneous differential privacy. Proc VLDB Endow, 2021, 15: 828–840
Acknowledgements
This work was supported in part by National Natural Science Foundation of China (Grant Nos. 62071296, 62002170, 62071234, U22A2002), National Key Research and Development Program of China (Grant No. 2020YFB1807700), Fundamental Research Funds for the Central Universities (Grant No. 30921013104), Key Technologies R&D Program of Jiangsu (Prospective and Key Technologies for Industry) (Grant Nos. BE2023022, BE2023022-2), Future Network Grant of Provincial Education Board in Jiangsu, Major Science and Technology Plan of Hainan Province (Grant No. ZDKJ2021022), Scientific Research Fund Project of Hainan University (Grant No. KYQD(ZR)-21008), Youth Foundation Project of Zhejiang Lab (Grant No. K2023PD0AA01), Collaborative Innovation Center of Information Technology, Hainan University (Grant No. XTCX2022XXC07), and Sciences and Technology Commission of Shanghai Municipality (Grant Nos. 22JC1404000, 20JC1416502, PKX2021-D02).
Author information
Authors and Affiliations
Corresponding author
Additional information
Supporting information Appendixes A–D. The supporting information is available online at info.scichina.com and springer.longhoe.net. The supporting materials are published as submitted, without typesetting or editing. The responsibility for scientific accuracy and content remains entirely with the authors.
Rights and permissions
About this article
Cite this article
Wei, K., Li, J., Ma, C. et al. Gradient sparsification for efficient wireless federated learning with differential privacy. Sci. China Inf. Sci. 67, 142303 (2024). https://doi.org/10.1007/s11432-023-3918-9
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11432-023-3918-9