[论文解读] Energy Efficient Federated Learning Over Wireless Communication Networks

Zhaohui Yang, Mingzhe Chen+3 more|arXiv (Cornell University)|Nov 6, 2019

Privacy-Preserving Technologies in Data参考文献 42被引用 53

一句话总结

本文提出了一种在无线网络上的联邦学习能量最小化框架，联合优化本地计算与传输资源以满足时延约束，迭代算法在能耗方面最高实现59.5%的降低。

ABSTRACT

In this paper, the problem of energy efficient transmission and computation resource allocation for federated learning (FL) over wireless communication networks is investigated. In the considered model, each user exploits limited local computational resources to train a local FL model with its collected data and, then, sends the trained FL model to a base station (BS) which aggregates the local FL model and broadcasts it back to all of the users. Since FL involves an exchange of a learning model between users and the BS, both computation and communication latencies are determined by the learning accuracy level. Meanwhile, due to the limited energy budget of the wireless users, both local computation energy and transmission energy must be considered during the FL process. This joint learning and communication problem is formulated as an optimization problem whose goal is to minimize the total energy consumption of the system under a latency constraint. To solve this problem, an iterative algorithm is proposed where, at every step, closed-form solutions for time allocation, bandwidth allocation, power control, computation frequency, and learning accuracy are derived. Since the iterative algorithm requires an initial feasible solution, we construct the completion time minimization problem and a bisection-based algorithm is proposed to obtain the optimal solution, which is a feasible solution to the original energy minimization problem. Numerical results show that the proposed algorithms can reduce up to 59.5% energy consumption compared to the conventional FL method.

研究动机与目标

• 在隐私与资源约束下，推动无线网络中的能效联邦学习（FL）的应用。
• 对本地计算和无线传输对FL时延与能量的耦合影响进行建模。
• 开发一个迭代资源分配算法，在时延约束下最小化总能量。

提出的方法

• 对带有本地计算和上行本地模型传输的FDMA蜂窝网络中的FL进行建模。
• 在本地计算精度和全局聚合下推导FL收敛速度。
• 将时域、带宽、功率、计算频率和学习精度等进行联合能量最小化建模。
• 提出一个低复杂度的迭代算法，对每个变量给出闭式更新。
• 通过完成时间最小化问题和二分搜索解法提供一个可行性查找步骤。
• 给出包含学习精度参数的Dinkelbach型优化等详细资源分配工作流程。

实验结果

研究问题

• RQ1 在无线资源约束下，本地计算精度与学习动态如何影响FL性能与收敛？
• RQ2 在时延约束和资源约束下，完成FL所需的最小总能量是多少？
• RQ3 如何在满足时延和数据传输要求的前提下，联合优化时间、带宽、功率、计算频率以最小化能量？
• RQ4 是否可以高效地找到一个可行的初始解以使能量最小化算法得以启动？
• RQ5 与传统未联合优化的FL相比，可以实现哪些能量节省？

主要发现

• 一种高效的联合计算与传输资源分配方案在与传统FL方法相比的总能耗上可降低多达59.5%。
• 本文在无线环境中结合本地计算精度和全局聚合推导了FL收敛速率。
• 提出一个含闭式解的迭代算法，可对时延、带宽、功率、计算频率和学习精度进行求解以实现能量最小化问题。
• 通过带有二分法的完成时间最小化方法，为能量优化提供了可行的起始点。
• 优化框架在时延约束下同时考虑本地计算能量和传输能量，取得了显著的能量节省。