Page 410 - 《软件学报》2026年第3期

刘建春 等: 基于块级多输出和知识自蒸馏的高效联邦学习框架 1373

00807]
[28] Fan X, Wang Y, Huo Y, Tian Z. Joint optimization of communications and federated learning over the air. IEEE Trans. on Wireless
Communications, 2022, 21(6): 4434–4449. [doi: 10.1109/TWC.2021.3130111]
[29] Ozkara K, Singh N, Data D, Diggavi S. QUPED: Quantized personalization via distillation with applications to federated learning. In:
Proc. of the 35th Int’l Conf. on Neural Information Processing Systems. Curran Associates Inc., 2021. 3622–3634.
[30] Chen MZ, Gündüz D, Huang KB, Saad W, Bennis M, Feljan AV, Poor HV. Distributed learning in wireless networks: Recent progress
and future challenges. IEEE Journal on Selected Areas in Communications, 2021, 39(12): 3579–3605. [doi: 10.1109/JSAC.2021.
3118346]
[31] Zhang L, Shen L, Ding L, Tao DC, Duan LY. Fine-tuning global model via data-free knowledge distillation for non-IID federated
learning. In: Proc. of the 2022 IEEE/CVF Conf. on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022. 10164–10173.
[doi: 10.1109/CVPR52688.2022.00993]
[32] Pillutla K, Kakade SM, Harchaoui Z. Robust aggregation for federated learning. IEEE Trans. on Signal Processing, 2022, 70: 1142–1154.
[doi: 10.1109/TSP.2022.3153135]
[33] He KM, Zhang XY, Ren SQ, Sun J. Deep residual learning for image recognition. In: Proc. of the 2016 IEEE Conf. on Computer Vision
and Pattern Recognition. Las Vegas: IEEE, 2016. 770–778. [doi: 10.1109/CVPR.2016.90]
[34] LeCun Y, Bengio Y, Hinton G. Deep learning. Nature, 2015, 521(7553): 436–444. [doi: 10.1038/nature14539]
[35] Liu JC, Xu HL, Zhao GM, Qian C, Fan XP, Huang LS. Incremental server deployment for scalable NFV-enabled networks. In: Proc. of
the 2020 IEEE Conf. on Computer Communications (INFOCOM 2020). Toronto: IEEE, 2020. 2361–2370. [doi: 10.1109/
INFOCOM41043.2020.9155364]
[36] de Boer PT, Kroese DP, Mannor S, Rubinstein RY. A tutorial on the cross-entropy method. Annals of Operations Research, 2005, 134(1):
19–67. [doi: 10.1007/s10479-005-5724-z]
[37] van Erven T, Harremoes P. Rényi divergence and Kullback-Leibler divergence. IEEE Trans. on Information Theory, 2014, 60(7):
3797–3820. [doi: 10.1109/TIT.2014.2320500]
[38] Acar DAE, Zhao Y, Zhu RZ, Navarro RM, Mattina M, Whatmough P, Saligrama V. Debiasing model updates for improving personalized
federated training. In: Proc. of the 38th Int’l Conf. on Machine Learning. 2021. 21–31.
[39] Paszke A, Gross S, Massa F, et al. PyTorch: An imperative style, high-performance deep learning library. In: Proc. of the 33rd Int’l Conf.
on Neural Information Processing Systems. Vancouver: Curran Associates Inc., 2019. 8026–8037.
[40] Liu JC, Xu HL, Wang L, Xu Y, Qian C, Huang JY, Huang H. Adaptive asynchronous federated learning in resource-constrained edge
computing. IEEE Trans. on Mobile Computing, 2023, 22(2): 674–690. [doi: 10.1109/TMC.2021.3096846]
[41] Krizhevsky A. Learning multiple layers of features from tiny images [MS. Thesis]. Department of Computer Science, University of
Toronto, 2009.
[42] Li QB, He BS, Song D. Model-contrastive federated learning. In: Proc. of the 2021 IEEE/CVF Conf. on Computer Vision and Pattern
Recognition. Nashville: IEEE, 2021. 10708–10717. [ doi: 10.1109/CVPR46437.2021.01057]
[43] Wang L, Xu Y, Xu HL, Jiang ZD, Chen M, Zhang WY, Qian C. BOSE: Block-wise federated learning in heterogeneous edge computing.
IEEE/ACM Trans. on Networking, 2024, 32(2): 1362–1377. [doi: 10.1109/TNET.2023.3316421]

附中文参考文献
[3] 施巍松, 孙辉, 曹杰, 张权, 刘伟. 边缘计算: 万物互联时代新型计算模型. 计算机研究与发展, 2017, 54(5): 907–924. [doi: 10.7544/
issn1000-1239.2017.20160941]

作者简介
刘建春, 博士, 副研究员, CCF 专业会员, 主要研究领域为物联网, 计算机网络, 边缘智能.
梁文艺, 硕士生, 主要研究领域为边缘智能, 流推理加速.
徐宏力, 博士, 教授, 博士生导师, CCF 专业会员, 主要研究领域为物联网, 计算机网络, 边缘智能.
马千飘, 博士, 副教授, CCF 专业会员, 主要研究领域为软件工程, 软件安全性, 形式化方法.
黄刘生, 博士, 教授, 博士生导师, CCF 高级会员, 主要研究领域为网络, 信息安全, 云计算, 大数据.