Page 409 - 《软件学报》2026年第3期

1372 软件学报 2026 年第 37 卷第 3 期

[4] McMahan B, Moore E, Ramage D, Hampson S, Arcas BAY. Communication-efficient learning of deep networks from decentralized data.
In: Proc. of the 20th Int’l Conf. on Artificial Intelligence and Statistics. 2017. 1273–1282.
[5] Zhang C, Xie Y, Bai H, Yu B, Li WH, Gao Y. A survey on federated learning. Knowledge-based Systems, 2021, 216: 106775. [doi: 10.
1016/j.knosys.2021.106775]
[6] Sattler F, Wiedemann S, Müller KR, Samek W. Robust and communication-efficient federated learning from non-IID data. IEEE Trans.
on Neural Networks and Learning Systems, 2020, 31(9): 3400–3413. [doi: 10.1109/TNNLS.2019.2944481]
[7] Hamer J, Mohri M, Suresh AT. FedBoost: A communication-efficient algorithm for federated learning. In: Proc. of the 37th Int’l Conf. on
Machine Learning. 2020. 3973–3983.
[8] Li T, Sahu AK, Zaheer M, Sanjabi M, Talwalkar A, Smith V. Federated optimization in heterogeneous networks. In: Proc. of the 3rd
MLSys Conf. 2020. 429–450.
[9] Kim J, Kim G, Han B. Multi-level branched regularization for federated learning. In: Proc. of the 39th Int’l Conf. on Machine Learning.
2022. 11058–11073.
[10] Chen HK, Frikha A, Krompass D, Gu JD, Tresp V. FRAug: Tackling federated learning with non-IID features via representation
augmentation. In: Proc. of the 2023 IEEE/CVF Int’l Conf. on Computer Vision. Paris: IEEE, 2023. 4826–4836. [doi: 10.1109/
ICCV51070.2023.00447]
[11] Jiang ZD, Xu Y, Xu HL, Wang ZY, Qiao CM, Zhao YM. FedMP: Federated learning through adaptive model pruning in heterogeneous
edge computing. In: Proc. of the 38th IEEE Int’l Conf. on Data Engineering (ICDE). Kuala Lumpur: IEEE, 2022. 767–779. [doi: 10.1109/
ICDE53745.2022.00062]
[12] Kim M, Yu S, Kim S, Moon SM. DepthFL: Depthwise federated learning for heterogeneous clients. In: Proc. of the 11th Int’l Conf. on
Learning Representations. 2022.
[13] Suvorov R, Logacheva E, Mashikhin A, Remizova A, Ashukha A, Silvestrov A, Kong N, Goka H, Park K, Lempitsky V. Resolution-
robust large mask inpainting with fourier convolutions. In: Proc. of the 2022 IEEE/CVF Winter Conf. on Applications of Computer
Vision. Waikoloa: IEEE, 2022. 3172–3182. [doi: 10.1109/WACV51458.2022.00323]
[14] Brown TB, Mann B, Ryder N, et al. Language models are few-shot learners. In: Proc. of the 34th Int’l Conf. on Neural Information
Processing Systems. Vancouver: Curran Associates Inc., 2020. 1877–1901.
[15] Zhang LF, Song JB, Gao AN, Chen JW, Bao CL, Ma KS. Be your own teacher: Improve the performance of convolutional neural
networks via self distillation. In: Proc. of the 2019 IEEE/CVF Int’l Conf. on Computer Vision. Seoul: IEEE, 2019. 3712–3721. [doi: 10.
1109/ICCV.2019.00381]
[16] Yang Q, Liu Y, Chen TJ, Tong YX. Federated machine learning: Concept and applications. ACM Trans. on Intelligent Systems and
Technology, 2019, 10(2): 12. [doi: 10.1145/3298981]
[17] Caldarola D, Dputo B, Ciccone M. Window-based model averaging improves generalization in heterogeneous federated learning. In:
Proc. of the 2023 IEEE/CVF Int’l Conf. on Computer Vision Workshops. Paris: IEEE, 2023. 2255–2263. [doi: 10.1109/ICCVW60793.
2023.00240]
[18] Zhu ZD, Hong JY, Zhou JY. Data-free knowledge distillation for heterogeneous federated learning. In: Proc. of the 38th Int’l Conf. on
Machine Learning. 2021. 12878–12889.
[19] Achituve I, Shamsian A, Navon A, Chechik G, Fetaya E. Personalized federated learning with Gaussian processes. In: Proc. of the 35th
Int’l Conf. on Neural Information Processing Systems. Curran Associates Inc., 2021. 8392–8406.
[20] Collins L, Hassani H, Mokhtari A, Shakkottai S. Exploiting shared representations for personalized federated learning. In: Proc. of the
38th Int’l Conf. on Machine Learning. 2021. 2089–2099.
[21] Zhang J, Guo S, Ma XS, Wang HZ, Xu WC, Wu FJ. Parameterized knowledge transfer for personalized federated learning. In: Proc. of
the 35th Int’l Conf. on Neural Information Processing Systems. Curran Associates Inc., 2021. 10092–10104.
[22] Marfoq O, Neglia G, Kameni L, Vidal R. Personalized federated learning through local memorization. In: Proc. of the 39th Int’l Conf. on
Machine Learning. 2022. 15070–15092.
[23] Stich SU, Cordonnier JB, Jaggi M. Sparsified SGD with memory. In: Proc. of the 32nd Int’l Conf. on Neural Information Processing
Systems. Montréal: Curran Associates Inc., 2018. 4452–4463.
[24] Basu D, Data D, Karakus C, Diggavi S. Qsparse-local-SGD: Distributed SGD with quantization, sparsification, and local computations.
In: Proc. of the 33rd Int’l Conf. on Neural Information Processing Systems. Vancouver: Curran Associates Inc., 2019. 14695–14706.
[25] Jiang Y, Wang SQ, Valls V, Ko BJ, Lee WH, Leung KK, Tassiulas L. Model pruning enables efficient federated learning on edge
devices. IEEE Trans. on Neural Networks and Learning Systems, 2023, 34(12): 10374–10386. [doi: 10.1109/TNNLS.2022.3166101]
[26] Tonellotto N, Gotta A, Nardini FM, Gadler D, Silvestri F. Neural network quantization in federated learning at the edge. Information
Sciences, 2021, 575: 417–436. [doi: 10.1016/j.ins.2021.06.039]
[27] Idelbayev Y, Carreira-Perpiñán MÁ. Low-rank compression of neural nets: Learning the rank of each layer. In: Proc. of the 2020
IEEE/CVF Conf. on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020. 8046–8056. [ doi: 10.1109/CVPR42600.2020.