Federated learning (FL) is a promising approach for solving multilingual tasks, potentially enabling clients with their own language-specific data to collaboratively construct a high-quality neural machine translation (NMT) model. However, communication constraints in practical network systems present challenges for exchanging large-scale NMT engines between FL parties. In this paper, we propose a meta-learning-based adaptive parameter selection methodology, MetaSend, that improves the communication efficiency of model transmissions from clients during FL-based multilingual NMT training. Our approach learns a dynamic threshold for filtering parameters prior to transmission without compromising the NMT model quality, based on the tensor deviations of clients between different FL rounds. Through experiments on two NMT datasets with different language distributions, we demonstrate that MetaSend obtains substantial improvements over baselines in translation quality in the presence of a limited communication budget.

翻译：联邦学习（FL）是解决多语言任务的一种有前景的方法，它使拥有各自语言特定数据的客户端能够协同构建高质量的神经机器翻译（NMT）模型。然而，实际网络系统中的通信约束给联邦学习各方之间交换大规模NMT引擎带来了挑战。本文提出一种基于元学习的自适应参数选择方法MetaSend，该方法能在基于联邦学习的多语言NMT训练过程中，提高客户端模型传输的通信效率。我们的方法根据客户端在不同联邦学习轮次之间的张量偏差，学习一个动态阈值，用于在传输前过滤参数，且不损害NMT模型质量。通过在两种不同语言分布的NMT数据集上进行实验，我们证明在有限通信预算下，MetaSend在翻译质量上相比基线方法取得了显著提升。