提出三项新方法，让联邦学习低秩分解更高效准确
The Panaceas for Improving Low-Rank Decomposition in Communication-Efficient Federated Learning
- 分三步优化：拆什么、怎么拆、如何聚合
- 比基线快收敛，精度提升显著，实验验证有效
- 适合关注通信效率与模型性能的联邦学习研究者
为提升联邦学习（FL）的训练效率，先前研究采用低秩分解技术以降低通信开销。本文旨在增强此类方法的性能，重点关注三个关键问题：应分解什么、如何分解以及如何聚合。为此，我们提出三种新方法：模型更新分解（MUD）、块级克罗内克分解（BKD）和聚合感知分解（AAD），分别针对上述问题。这些方法具有互补性，可同时应用以达到最优效果。此外，我们提供了严格的理论分析，保证所提MUD的收敛性。大量实验结果表明，该方法在收敛速度和精度上均优于现有基线方法。代码已公开于 https://github.com/Leopold1423/fedmud-icml25。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。