Entropy-Constrained VQ-VAE for Deep-Learning-Based CSI Feedback

Deep-learning (DL)-based channel state information (CSI) feedback has attracted a great deal of attention due to its effectiveness in compressing CSI in massive multiple-input multiple-output systems. This technique harnesses an autoencoder architecture, where an encoder network transforms CSI into...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on vehicular technology Vol. 74; no. 6; pp. 9870 - 9875
Main Authors: Shin, Junyong, Park, Jinsung, Jeon, Yo-Seb
Format: Journal Article
Language:English
Published: New York IEEE 01.06.2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Autoencoders
Channel state information (CSI) feedback
Coders
Decoding
Deep learning
deep-learning-based feedback
Discrete Fourier transforms
Entropy
Entropy coding
entropy constrained vector quantization
Feedback
Feedback control systems
Harnesses
Information systems
Massive MIMO
Modules
Rate-distortion
Training
Vector quantization
vector-quantized variational autoencoder (VQ-VAE)
Vectors
ISSN:0018-9545, 1939-9359
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Deep-learning (DL)-based channel state information (CSI) feedback has attracted a great deal of attention due to its effectiveness in compressing CSI in massive multiple-input multiple-output systems. This technique harnesses an autoencoder architecture, where an encoder network transforms CSI into a low-dimensional latent vector, and a decoder network reconstructs the CSI from the latent vector. In this paper, we propose a vector quantization (VQ) framework for DL-based CSI feedback to provide an efficient finite-bit representation of the latent vector. In our framework, a trainable VQ module is employed after the encoder network, and entropy coding is applied to the output of the VQ module. To jointly train the encoder and decoder networks with the VQ codebook, we design a quantization criterion and loss function of vector-quantized variational autoencoder based on the rate-distortion theory. We also devise two practical strategies to make the proposed framework applicable under a strict bit budget constraint. Using simulations, we demonstrate that DL-based CSI feedback with the proposed framework outperforms existing quantization-aware DL-based CSI feedback methods.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0018-9545
1939-9359
DOI:10.1109/TVT.2025.3542267