Communication-Efficient Federated Learning Over MIMO Multiple Access Channels

Yo–Seb Jeon

doi:10.1109/TCOMM.2022.3198433

Communication-Efficient Federated Learning Over MIMO Multiple Access Channels

2022-10-01

10

OA

AI

Y

Yo–Seb Jeon

M

Mohammad Mohammadi Amiri

N

Namyoon Lee *

DOI：10.1109/TCOMM.2022.3198433

原文链接

原文求助

摘要

En 中文

Communication efficiency is of importance for wireless federated learning systems. In this paper, we propose a communication-efficient strategy for federated learning over multiple-input multiple-output (MIMO) multiple access channels (MACs). The proposed strategy comprises two components. When sending a locally computed gradient, each device compresses a high dimensional local gradient to multiple lower-dimensional gradient vectors using block sparsification. When receiving a superposition of the compressed local gradients via a MIMO-MAC, a parameter server (PS) performs a joint MIMO detection and the sparse local-gradient recovery. Inspired by the turbo decoding principle, our joint detection-and-recovery algorithm accurately recovers the high-dimensional local gradients by iteratively exchanging their beliefs for MIMO detection and sparse local gradient recovery outputs. We then analyze the reconstruction error of the proposed algorithm and its impact on the convergence rate of federated learning. From simulations, our gradient compression and joint detection-and-recovery methods diminish the communication cost significantly while achieving identical classification accuracy for the case without any compression.

Keyword:

Collaborative work

Wireless communication

MIMO communication

Uplink

Image reconstruction

Convergence

Computational modeling

Federated learning

distributed machine learning

gradient compression

gradient reconstruction

compressed sensing

Communication-Efficient Federated Learning Over MIMO Multiple Access Channels

摘要

期刊

机构