This paper presents a study on asynchronous Federated Learning (FL) in a mobile network setting. The majority of FL algorithms assume that communication between clients and the server is always available, however, this is not the case in many real-world systems. To address this issue, the paper explores the impact of mobility on the convergence performance of asynchronous FL. By exploiting mobility, the study shows that clients can indirectly communicate with the server through another client serving as a relay, creating additional communication opportunities. This enables clients to upload local model updates sooner or receive fresher global models. We propose a new FL algorithm, called FedMobile, that incorporates opportunistic relaying and addresses key questions such as when and how to relay. We prove that FedMobile achieves a convergence rate $O(\frac{1}{\sqrt{NT}})$, where $N$ is the number of clients and $T$ is the number of communication slots, and show that the optimal design involves an interesting trade-off on the best timing of relaying. The paper also presents an extension that considers data manipulation before relaying to reduce the cost and enhance privacy. Experiment results on a synthetic dataset and two real-world datasets verify our theoretical findings.

翻译：本文研究了移动网络环境下的异步联邦学习（FL）。大多数FL算法假设客户端与服务器之间的通信始终可用，但在许多实际系统中并非如此。为解决这一问题，本文探讨了移动性对异步FL收敛性能的影响。通过利用移动性，研究表明客户端可以借助作为中继的另一客户端间接与服务器通信，从而创造额外的通信机会。这使得客户端能够更早地上传本地模型更新或获取更新的全局模型。我们提出了一种名为FedMobile的新型FL算法，该算法融合了机会型中继，并解决了中继时机与方式等关键问题。我们证明FedMobile实现了收敛速率$O(\frac{1}{\sqrt{NT}})$，其中$N$为客户端数量，$T$为通信时隙数，并表明最优设计涉及中继最佳时机的有趣权衡。本文还提出了一种扩展方案，在中继前对数据进行操作以降低成本并增强隐私性。在合成数据集和两个真实世界数据集上的实验结果验证了我们的理论发现。