Federated Learning (FL) can be used in mobile edge networks to train machine learning models in a distributed manner. Recently, FL has been interpreted within a Model-Agnostic Meta-Learning (MAML) framework, which brings FL significant advantages in fast adaptation and convergence over heterogeneous datasets. However, existing research simply combines MAML and FL without explicitly addressing how much benefit MAML brings to FL and how to maximize such benefit over mobile edge networks. In this paper, we quantify the benefit from two aspects: optimizing FL hyperparameters (i.e., sampled data size and the number of communication rounds) and resource allocation (i.e., transmit power) in mobile edge networks. Specifically, we formulate the MAML-based FL design as an overall learning time minimization problem, under the constraints of model accuracy and energy consumption. Facilitated by the convergence analysis of MAML-based FL, we decompose the formulated problem and then solve it using analytical solutions and the coordinate descent method. With the obtained FL hyperparameters and resource allocation, we design a MAML-based FL algorithm, called Automated Federated Learning (AutoFL), that is able to conduct fast adaptation and convergence. Extensive experimental results verify that AutoFL outperforms other benchmark algorithms regarding the learning time and convergence performance.

翻译：联邦学习（FL）可在移动边缘网络中用于以分布式方式训练机器学习模型。近期，FL被纳入模型无关元学习（MAML）框架中进行解释，这为FL在处理异构数据集时带来了快速适应与收敛的显著优势。然而，现有研究仅简单结合MAML与FL，未明确解决MAML能为FL带来多大益处，以及如何在移动边缘网络中最大化该益处。本文从两方面量化该益处：优化移动边缘网络中的FL超参数（即采样数据量与通信轮数）及资源分配（即发射功率）。具体而言，我们将基于MAML的FL设计建模为一个在模型精度与能耗约束下的总学习时间最小化问题。借助MAML-based FL的收敛性分析，我们对所提问题进行了分解，并利用解析解与坐标下降法进行求解。基于获得的FL超参数与资源分配，我们设计了一种基于MAML的FL算法，称为自动化联邦学习（AutoFL），该算法能够实现快速适应与收敛。大量实验结果表明，AutoFL在学习时间与收敛性能方面均优于其他基准算法。