Page 286 - 《软件学报》2026年第6期

薛大暄 等: 基于差分隐私的通信高效联邦推荐方法 2605

framework. IEEE Trans. on Knowledge and Data Engineering, 2023, 35(4): 3912–3924. [doi: 10.1109/TKDE.2021.3130265]
[27] Wang H, Zhou H, Lit MZ, Zhao L, Leung VCM. Federated distributed deep reinforcement learning for recommendation-enabled edge
caching. In: Proc. of the 2024 IEEE Conf. on Computer Communications Workshops (INFOCOM WKSHPS). Vancouver: IEEE, 2024.
1–2. [doi: 10.1109/INFOCOMWKSHPS61880.2024.10620845]
[28] Qi T, Wu FZ, Wu CH, Huang YF, Xie X. Uni-FedRec: A unified privacy-preserving news recommendation framework for model training
and online serving. In: Findings of the Association for Computational Linguistics: EMNLP 2021. Punta: ACL, 2021. 1438–1448. [doi: 10.
18653/v1/2021.findings-emnlp.124]
[29] Liang F, Pan WK, Ming Z. FedRec++: Lossless federated recommendation with explicit feedback. In: Proc. of the 35th AAAI Conf. on
Artificial Intelligence. AAAI Press, 2021. 4224–4231. [doi: 10.1609/aaai.v35i5.16546]
[30] Liu SC, Ge YQ, Xu SY, Zhang YF, Marian A. Fairness-aware federated matrix factorization. In: Proc. of the 16th ACM Conf. on
Recommender Systems. Seattle: ACM, 2022. 168–178. [doi: 10.1145/3523227.3546771]
[31] Lin YJ, Ren PJ, Chen ZM, Ren ZC, Yu DX, Ma J, de Rijke M, Cheng XZ. Meta matrix factorization for federated rating predictions. In:
Proc. of the 43rd Int’l ACM SIGIR Conf. on Research and Development in Information Retrieval. ACM, 2020: 981–990. [doi: 10.1145/
3397271.3401081]
[32] Yang EY, Huang YF, Liang F, Pan WK, Ming Z. FCMF: Federated collective matrix factorization for heterogeneous collaborative
filtering. Knowledge-based Systems, 2021, 220: 106946. [doi: 10.1016/j.knosys.2021.106946]
[33] Lin ZH, Pan WK, Yang Q, Ming Z. A generic federated recommendation framework via fake marks and secret sharing. ACM Trans. on
Information Systems, 2022, 41(2): 40. [doi: 10.1145/3548456]
[34] He XN, Liao LZ, Zhang HW, Nie LQ, Hu X, Chua TS. Neural collaborative filtering. In: Proc. of the 26th Int’l Conf. on World Wide
Web. Perth: Int’l World Wide Web Conferences Steering Committee, 2017. 173–182. DOI: 10.1145/3038912.3052569
[35] Zhang H, Wu B, Yuan XL, Pan SR, Tong HH, Pei J. Trustworthy graph neural networks: Aspects, methods, and trends. Proc. of the
IEEE, 2024, 112(2): 97–139. [doi: 10.1109/JPROC.2024.3369017]
[36] Lei RZ, Wang PH, Zhao JZ, Lan L, Tao J, Deng C, Feng JL, Wang XD, Guan XH. Federated learning over coupled graphs. IEEE Trans.
on Parallel and Distributed Systems, 2023, 34(4): 1159–1172. [doi: 10.1109/TPDS.2023.3240527]
[37] Wu CH, Wu FZ, Lyu L, Qi T, Huang YF, Xie X. A federated graph neural network framework for privacy-preserving personalization.
Nature Communications, 2022, 13(1): 3091. [doi: 10.1038/s41467-022-30714-9]
[38] Lin YJ, Han S, Mao HZ, Wang Y, Dally B. Deep gradient compression: Reducing the communication bandwidth for distributed training.
In: Proc. of the 2018 Int’l Conf. on Learning Representations. OpenReview.net, 2018.
[39] Rothchild D, Panda A, Ullah E, Ivkin N, Stoica I, Braverman V, Gonzalez J, Arora R. FetchSGD: Communication-efficient federated
learning with sketching. In: Proc. of the 37th Int’l Conf. on Machine Learning. PMLR, 2020. 8253–8265.
[40] Yun WJ, Kwak Y, Baek H, Jung S, Ji MY, Bennis M, Park J, Kim J. SlimFL: Federated learning with superposition coding over
slimmable neural networks. IEEE/ACM Trans. on Networking, 2023, 31(6): 2499–2514. [doi: 10.1109/TNET.2022.3231864]
[41] Chai D, Wang LY, Zhang JX, Yang L, Cai SW, Chen K, Yang Q. Practical lossless federated singular vector decomposition over billion-
scale data. In: Proc. of the 28th ACM SIGKDD Conf. on Knowledge Discovery and Data Mining. Washington: ACM, 2022. 46–55. [doi:
10.1145/3534678.3539402]
[42] Chen HC, Vikalo H. Heterogeneity-guided client sampling: Towards fast and efficient Non-IID federated learning. In: Proc. of the 38th Int’l
Conf. on Neural Information Processing Systems. Vancouver: Curran Associates Inc., 2024. 2093.
[43] Nguyen J, Malik K, Zhan H, Yousefpour A, Rabbat M, Malek M, Huba D. Federated learning with buffered asynchronous aggregation.
In: Proc. of the 2022 Int’l Conf. on Artificial Intelligence and Statistics. Valencia: PMLR, 2022. 3581–3607.
[44] Tang ZH, Shi SH, Li B, Chu XW. GossipFL: A decentralized federated learning framework with sparsified and adaptive communication.
IEEE Trans. on Parallel and Distributed Systems, 2023, 34(3): 909–922. [doi: 10.1109/TPDS.2022.3230938]
[45] Kim M, Saad W, Debbah M, Hong CS. SpaFL: Communication-efficient federated learning with sparse models and low computational
overhead. In: Proc. of the 38th Int’l Conf. on Neural Information Processing Systems. ACM, 2024. 86500–86527.
[46] Wang ZY, Xu HL, Xu Y, Jiang ZD, Liu JC, Chen S. FAST: Enhancing federated learning through adaptive data sampling and local
training. IEEE Trans. on Parallel and Distributed Systems, 2024, 35(2): 221–236. [doi: 10.1109/TPDS.2023.3334398]
[47] Dwork C, McSherry F, Nissim K, Smith A. Calibrating noise to sensitivity in private data analysis. In: Proc. of 3rd Theory of
Cryptography Conf. on Theory of Cryptography. New York: Springer, 2006. 265–284. [doi: 10.1007/11681878_14]
[48] Dwork C. Differential privacy. In: van Tilborg HCA, Jajodia S, eds. Encyclopedia of Cryptography and Security. New York: Springer,
2011. 338–340. [doi: 10.1007/978-1-4419-5906-5_752]
[49] Warner SL. Randomized response: A survey technique for eliminating evasive answer bias. Journal of the American Statistical