arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2104.12416cs.LGcs.DC
收藏

具有双边低秩压缩的通信高效的联邦学习

Communication-Efficient Federated Learning with Dual-Side Low-Rank Compression

The Hong Kong University of Science and Technology(香港科技大学);The Hong Kong Polytechnic University(香港理工大学);Peng Cheng Laboratory(鹏城实验室)

Zhefeng Qiao, Xianghao Yu, Jun Zhang, Khaled B. Letaief

摘要:

联邦学习(FL)是一种很有前途且功能强大的方法,用于在不共享客户端原始数据的情况下训练深度学习模型。在FL的训练过程中,中心服务器和分布式客户端需要定期交换大量的模型信息。为了应对通信密集型训练的挑战,我们提出了一种新的训练方法,称为双侧低秩压缩(FedDLR)的联邦学习,其中深度学习模型在服务器和客户端都通过低秩近似进行压缩。建议FedDLR不仅减少了在训练阶段的通信开销,但也直接生成一个紧凑的模型,以加快推理过程。我们将提供收敛性分析,调查的关键参数的影响,并实证表明,FedDLR优于国家的最先进的解决方案在通信和计算效率方面。

英文摘要:

Federated learning (FL) is a promising and powerful approach for training deep learning models without sharing the raw data of clients. During the training process of FL, the central server and distributed clients need to exchange a vast amount of model information periodically. To address the challenge of communication-intensive training, we propose a new training method, referred to as federated learning with dual-side low-rank compression (FedDLR), where the deep learning model is compressed via low-rank approximations at both the server and client sides. The proposed FedDLR not only reduces the communication overhead during the training stage but also directly generates a compact model to speed up the inference process. We shall provide convergence analysis, investigate the influence of the key parameters, and empirically show that FedDLR outperforms the state-of-the-art solutions in terms of both the communication and computation efficiency.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑