此研究提出了一種新的無線知識暫存機制，在這個機制中機器學習模型可以暫存在基地台中，從而使得聯邦學習的訓練更加高效且減少基地台內的用戶獲取模型時的資源消耗。在此研究中，我們首先考慮了單基地台場景。在此場景中，我們通過在暫存存儲容量、通訊和計算延遲以及總能量消耗的約束下最小化訓練誤差來確定暫存決策、用戶選擇和無線資源分配。具體做法是首先計算每個模型的最小可實現訓練損失，再最佳化二元暫存變量來獲得解決方案，其中後者可以簡化為 0-1背包問題。在此基礎上，我們將提出的框架擴展到多基地台場景，與此同時必須進一步確定基地台之間的用戶關聯。我們採用對偶上升（dual-ascent）方法，即在每次迭代中引入和更新拉格朗日乘子（Lagrange multiplier）以正則化用戶選擇和用戶關聯之間的依賴關係。在給定拉格朗日乘子下，暫存決策、用戶選擇、無線資源分配和用戶關聯變量可以依次使用區塊坐標下降（block coordinate descent）法進行優化。由模擬可見，在兩種場景下，我們所提出的方案與僅考慮用戶偏好暫存和隨機暫存策略相比可以實現更低的訓練誤差。

This work examines a novel wireless knowledge caching framework where machine learning models are cached at local small cell base-stations (SBS) to facilitate both federated training and access of the models by cellular users. We first consider a single-SBS scenario, where the caching decision, user selection, and wireless resource allocation are jointly determined by minimizing a training error bound subject to constraints on the cache storage capacity, the communication and computation latency, and the total energy consumption. The solution is obtained by first computing the minimum achievable training loss for each model, followed by the optimization of the binary caching variables, which reduces to a 0-1 Knapsack problem. The proposed framework is then extended to the multiple-SBS scenario where the user association among SBSs must be further examined. We adopt a dual-ascent method where Lagrange multipliers are introduced and updated in each iteration to regularize the dependence among user selection and association. Given the Lagrange multipliers, the caching decision, user selection, wireless resource allocation and user association variables are optimized in turn using a block coordinate descent algorithm. Simulations show that the proposed scheme can achieve lower training error bounds compared to preference-only and random caching policies in both scenarios.

Abstract i
Contents ii
1 Introduction 1
2 Review of Federated Learning 6
3 System Model 10
4 Joint Model Caching, Resource Allocation, and User Selection for the Single-SBS Scenario 14
4.1 Inner Optimization of the Resource Allocation and User Selection . . . . . . . . . 16
4.2 Outer Optimization of the Knowledge Caching Policy . . . . . . . . . . . . . . . 19
5 Joint User Association, Model Caching, Resource Allocation, and User Selection for
the Multiple-SBS Scenario 21
5.1 Optimization of Θ given Λ[t] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25
5.1.1 Optimization of Θ1 given Θ2 = Θ˜ 2 and Λ[t] . . . . . . . . . . . . . . . . 255.1.2 Optimization of Θ2 given Θ1 = Θ˜ 1 and Λ[t] . . . . . . . . . . . . . . . . 28
5.2 Update of Dual Variable Λ . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 29
6 Numerical Simulations 32
7 Conclusion 39

[1] B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. A. y Arcas, “Communicationefficient learning of deep networks from decentralized data,” in Proc. Int. Conf. Artif. Intell. Stat. (AISTATS), vol. 54, 2017, pp. 1273–1282.
[2] K. Shanmugam, N. Golrezaei, A. G. Dimakis, A. F. Molisch, and G. Caire, “Femtocaching:
Wireless content delivery through distributed caching helpers,” IEEE Trans. Inf. Theory,
vol. 59, no. 12, pp. 8402–8413, 2013.
[3] L. Li, G. Zhao, and R. S. Blum, “A survey of caching techniques in cellular networks: Research issues and challenges in content placement and delivery strategies,” IEEE Commun.
Surveys Tuts., vol. 20, no. 3, pp. 1710–1732, 2018.
[4] S. H. Chae and W. Choi, “Caching placement in stochastic wireless caching helper networks: Channel selection diversity via caching,” IEEE Trans. Commun., vol. 15, no. 10, pp. 6626–6637, 2016.
[5] B. Zhou, Y. Cui, and M. Tao, “Optimal dynamic multicast scheduling for cache-enabled
content-centric wireless networks,” IEEE Trans. Commun., vol. 65, no. 7, pp. 2956–2970,
2017.
[6] C. Yang, Y. Yao, Z. Chen, and B. Xia, “Analysis on cache-enabled wireless heterogeneous
networks,” IEEE Trans. Wireless Commun., vol. 15, no. 1, pp. 131–145, 2015.
[7] K. Li, C. Yang, Z. Chen, and M. Tao, “Optimization and analysis of probabilistic caching in
n-tier heterogeneous networks,” IEEE Trans. Wireless Commun., vol. 17, no. 2, pp. 1283–
1297, 2017.
[8] Z. Chen, J. Lee, T. Q. Quek, and M. Kountouris, “Cooperative caching and transmission
design in cluster-centric small cell networks,” IEEE Trans. Wireless Commun., vol. 16, no. 5,
pp. 3401–3415, 2017.
[9] M.-C. Lee and A. F. Molisch, “Caching policy and cooperation distance design for base station assisted wireless D2D caching networks: Throughput and energy efficiency optimization
and trade-off,” IEEE Trans. Wireless Commun., vol. 17, no. 11, pp. 7500–7514, 2018.
[10] M.-C. Lee, M. Ji, A. F. Molisch, and N. Sastry, “Throughput–outage analysis and evaluation
of cache-aided d2d networks with measured popularity distributions,” IEEE Trans. Wireless
Commun., vol. 18, no. 11, pp. 5316–5332, 2019.
[11] Z. Yang, M. Chen, W. Saad, C. S. Hong, and M. Shikh-Bahaei, “Energy efficient federated
learning over wireless communication networks,” IEEE Trans. Wireless Commun., vol. 20,
no. 3, pp. 1935–1949, 2021.
[12] S. Zheng, C. Shen, and X. Chen, “Design and analysis of uplink and downlink communications for federated learning,” IEEE J. Sel. Areas Commun., vol. 39, no. 7, pp. 2150–2167, 2020.
[13] S. Wang, T. Tuor, T. Salonidis, K. K. Leung, C. Makaya, T. He, and K. Chan, “Adaptive federated learning in resource constrained edge computing systems,” IEEE J. Sel. Areas Commun., vol. 37, no. 6, pp. 1205–1221, 2019.
[14] M. Chen, Z. Yang, W. Saad, C. Yin, H. V. Poor, and S. Cui, “A joint learning and communications framework for federated learning over wireless networks,” IEEE Trans. Wireless Commun., vol. 20, no. 1, pp. 269–283, 2021.
[15] W. Shi, S. Zhou, Z. Niu, M. Jiang, and L. Geng, “Joint device scheduling and resource allocation for latency constrained wireless federated learning,” IEEE Trans. Wireless Commun., vol. 20, no. 1, pp. 453–467, 2020.
[16] H. H. Yang, Z. Liu, T. Q. Quek, and H. V. Poor, “Scheduling policies for federated learning
in wireless networks,” IEEE Trans. Commun., vol. 68, no. 1, pp. 317–333, 2020.
[17] Y. He, J. Ren, G. Yu, and J. Yuan, “Importance-aware data selection and resource allocation in federated edge learning system,” IEEE Trans. Veh. Technol., vol. 69, no. 11, pp. 13 593–13 605, 2020.
[18] M. M. Wadu, S. Samarakoon, and M. Bennis, “Joint client scheduling and resource allocation under channel uncertainty in federated learning,” IEEE Trans. Commun., 2021.
[19] H. T. Nguyen, V. Sehwag, S. Hosseinalipour, C. G. Brinton, M. Chiang, and H. V. Poor,
“Fast-convergent federated learning,” IEEE J. Sel. Areas Commun., vol. 39, no. 1, pp. 201–
218, 2020.
[20] M. M. Amiri, D. Gund ¨ uz, S. R. Kulkarni, and H. V. Poor, “Convergence of update aware device scheduling for federated learning at the wireless edge,” IEEE Trans. Wireless Commun., vol. 20, no. 6, pp. 3643–3658, 2021.
[21] C. T. Dinh, N. H. Tran, M. N. Nguyen, C. S. Hong, W. Bao, A. Y. Zomaya, and V. Gramoli,
“Federated learning over wireless networks: Convergence analysis and resource allocation,”
IEEE/ACM Trans. Netw., vol. 29, no. 1, pp. 398–409, 2020.
[22] C. Feng, Y. Wang, Z. Zhao, T. Q. Quek, and M. Peng, “Joint optimization of data sampling and user selection for federated learning in the mobile edge computing systems,” in Proc.
IEEE Int. Conf. Commun. Workshops (ICC Workshops), 2020, pp. 1–6.
[23] J. Ren, Y. He, D. Wen, G. Yu, K. Huang, and D. Guo, “Scheduling for cellular federated edge learning with importance and channel awareness,” IEEE Trans. Wireless Commun., vol. 19, no. 11, pp. 7690–7703, 2020.
[24] K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image
recognition,” in Proc. Int. Conf. Learn. Represent. (ICLR), 2015.
[25] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2016, pp. 770–778.
[26] A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, and
H. Adam, “Mobilenets: Efficient convolutional neural networks for mobile vision applications,” arXiv:1704.04861, 2017.
[27] H. Q. Le, H. Al-Shatri, and A. Klein, “Efficient resource allocation in mobile-edge computation offloading: Completion time minimization,” in Proc. IEEE Int. Symp. Inf. Theory (ISIT), 2017, pp. 2513–2517.
[28] N. H. Tran, W. Bao, A. Zomaya, N. M. NH, and C. S. Hong, “Federated learning over wireless networks: Optimization model design and analysis,” in Proc. IEEE Int. Conf. Comput.
Commun. (INFOCOM), 2019, pp. 1387–1395.
[29] S. Martello, “Knapsack problems: algorithms and computer implementations, WileyInterscience series in discrete mathematics and optimization, 1990.
[30] H. Kellerer, U. Pferschy, and D. Pisinger, Knapsack problems. Springer, 2004.
[31] S. Boyd, N. Parikh, and E. Chu, Distributed optimization and statistical learning via the
alternating direction method of multipliers. Now Publishers Inc, 2011.
[32] D. Bertsekas, Nonlinear Programming. Athena Scientific, 1999.
[33] D. G. Cattrysse and L. N. Van Wassenhove, “A survey of algorithms for the generalized
assignment problem,” European Journal of Operational Research, vol. 60, no. 3, pp. 260–
272, 1992.
[34] R. Cohen, L. Katzir, and D. Raz, “An efficient approximation for the generalized assignment problem,” Information Processing Letters, vol. 100, no. 4, pp. 162–166, 2006.
[35] Q. Zeng, Y. Du, K. Huang, and K. K. Leung, “Energy-efficient radio resource allocation for
federated edge learning,” in Proc. IEEE Int. Conf. Commun. Workshops (ICC Workshops),
2020, pp. 1–6.
[36] M.-C. Lee, A. F. Molisch, N. Sastry, and A. Raman, “Individual preference probability
modeling and parameterization for video content in wireless caching networks,” IEEE/ACM
Trans. Netw., vol. 27, no. 2, pp. 676–690, 2019.