Reducing Complexity of CSI Feedback based on Deep Learning for Massive MIMO using Tensor-Train Decomposition

To further reduce the complexity of the channel state information (CSI) based on deep learning for massive multiple inputs and multiple outputs (MIMO) system, we propose a method called TT-CsiNet, based on the original CsiNet framework, using Tensor-Train decomposition to decompose the weights of th...

Full description

Saved in:
Bibliographic Details
Main Authors: Cen, Xiangyu, Lam, Chan-Tong, Liang, Yuanhui, Xu, Man, Ng, Benjamin, Im, Sio Kei
Format: Conference Proceeding
Language:English
Subjects:
Channel state information
Computational complexity
Computational modeling
CSI feedback
Deep learning
Massive MIMO
Memory management
model compression
Quantization (signal)
tensor-train decomposition
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:To further reduce the complexity of the channel state information (CSI) based on deep learning for massive multiple inputs and multiple outputs (MIMO) system, we propose a method called TT-CsiNet, based on the original CsiNet framework, using Tensor-Train decomposition to decompose the weights of the fully-connected layers, at the UE side. Experimental results show that the memory requirement is reduced by 99% of the original CsiNet for UEs, depending on the compression ratio. Moreover, TT-CsiNet can reduce the number of floating point operations (FLOPs) by about 17.27% to 80.44%, depending on the compression ratio. In addition, TT-CsiNet has comparable performance to the original CsiNet and other variants of the low complexity CsiNet using pruning, quantization, and weight clustering.
ISSN:2837-7109
DOI:10.1109/ICCC59590.2023.10507483