Low-Rank Gradient Compression with Error Feedback for MIMO Wireless Federated Learning
CoRR(2024)
摘要
This paper presents a novel approach to enhance the communication efficiency
of federated learning (FL) in multiple input and multiple output (MIMO)
wireless systems. The proposed method centers on a low-rank matrix
factorization strategy for local gradient compression based on alternating
least squares, along with over-the-air computation and error feedback. The
proposed protocol, termed over-the-air low-rank compression (Ota-LC), is
demonstrated to have lower computation cost and lower communication overhead as
compared to existing benchmarks while guaranteeing the same inference
performance. As an example, when targeting a test accuracy of 80
Cifar-10 dataset, Ota-LC achieves a reduction in total communication costs of
at least 30
computational complexity order by a factor equal to the sum of the dimension of
the gradients.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要