标题： 通信高效联邦学习中提升低秩分解的万能药 显示英文标题

标题： The Panaceas for Improving Low-Rank Decomposition in Communication-Efficient Federated Learning

摘要： 为了提高联邦学习（FL）的训练效率，以往的研究采用了低秩分解技术来减少通信开销。本文旨在提升这些低秩分解方法的性能。具体来说，我们关注联邦学习中与分解相关的三个关键问题：分解什么、如何分解以及如何聚合。随后，我们引入了三种新颖的技术：模型更新分解（MUD）、块级Kronecker分解（BKD）和聚合感知分解（AAD），每种技术针对特定的问题。这些技术是互补的，可以同时应用以实现最佳性能。此外，我们还提供了严格的理论分析，以确保所提出的MUD的收敛性。广泛的实验结果表明，我们的方法相较于相关基线方法具有更快的收敛速度和更高的准确性。代码可在https://github.com/Leopold1423/fedmud-icml25获取。 显示英文摘要

摘要： To improve the training efficiency of federated learning (FL), previous research has employed low-rank decomposition techniques to reduce communication overhead. In this paper, we seek to enhance the performance of these low-rank decomposition methods. Specifically, we focus on three key issues related to decomposition in FL: what to decompose, how to decompose, and how to aggregate. Subsequently, we introduce three novel techniques: Model Update Decomposition (MUD), Block-wise Kronecker Decomposition (BKD), and Aggregation-Aware Decomposition (AAD), each targeting a specific issue. These techniques are complementary and can be applied simultaneously to achieve optimal performance. Additionally, we provide a rigorous theoretical analysis to ensure the convergence of the proposed MUD. Extensive experimental results show that our approach achieves faster convergence and superior accuracy compared to relevant baseline methods. The code is available at https://github.com/Leopold1423/fedmud-icml25.