Many compression techniques have been proposed to reduce the communication overhead of Federated Learning training procedures. However, these are typically designed for compressing model updates, which are expected to decay throughout training. As a result, such methods are inapplicable to downlink (i.e., from the parameter server to clients) compression in the cross-device setting, where heterogeneous clients $\textit{may appear only once}$ during training and thus must download the model parameters. In this paper, we propose a new framework ($\texttt{DoCoFL}$) for downlink compression in the cross-device federated learning setting. Importantly, $\texttt{DoCoFL}$ can be seamlessly combined with many uplink compression schemes, rendering it suitable for bi-directional compression. Through extensive evaluation, we demonstrate that $\texttt{DoCoFL}$ offers significant bi-directional bandwidth reduction while achieving competitive accuracy to that of $\texttt{FedAvg}$ without compression.

翻译：许多压缩技术已被提出，用于减少联邦学习训练过程中的通信开销。然而，这些技术通常设计用于压缩模型更新，而模型更新在训练过程中预计会逐渐衰减。因此，这类方法不适用于跨设备场景中的下行链路（即从参数服务器到客户端）压缩——在该场景中，异构客户端在训练期间$\textit{可能仅出现一次}$，因此必须下载完整的模型参数。本文提出了一种新的框架（$\texttt{DoCoFL}$），用于跨设备联邦学习环境中的下行链路压缩。重要的是，$\texttt{DoCoFL}$可无缝地与多种上行链路压缩方案结合，从而适用于双向压缩。通过广泛评估，我们证明$\texttt{DoCoFL}$在实现显著双向带宽缩减的同时，其准确率可达到与无压缩的$\texttt{FedAvg}$相当的竞争力水平。