The Panaceas for Improving Low-Rank Decomposition in Communication-Efficient Federated Learning
This work addresses communication bottlenecks in federated learning, offering incremental improvements to existing decomposition methods.
The paper tackles the problem of improving low-rank decomposition techniques in federated learning to reduce communication overhead, introducing three novel methods (MUD, BKD, AAD) that achieve faster convergence and superior accuracy compared to baselines.
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.