Context-Aware Deep Learning for Robust Channel Extrapolation in Fluid Antenna Systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jin, Yanliang, Yu, Runze, Gao, Yuan, Liu, Shengli, Chu, Xiaoli, Wong, Kai-Kit, Chae, Chan-Byoung
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917224234614784
author Jin, Yanliang
Yu, Runze
Gao, Yuan
Liu, Shengli
Chu, Xiaoli
Wong, Kai-Kit
Chae, Chan-Byoung
author_facet Jin, Yanliang
Yu, Runze
Gao, Yuan
Liu, Shengli
Chu, Xiaoli
Wong, Kai-Kit
Chae, Chan-Byoung
contents Fluid antenna systems (FAS) offer remarkable spatial flexibility but face significant challenges in acquiring high-resolution channel state information (CSI), leading to considerable overhead. To address this issue, we propose CANet, a robust deep learning model for channel extrapolation in FAS. CANet combines context-adaptive modeling with a cross-scale attention mechanism and is built on a ConvNeXt v2 backbone to improve extrapolation accuracy for unobserved antenna ports. To further enhance robustness, we introduce a novel spatial amplitude perturbation strategy, inspired by frequency-domain augmentation techniques in image processing. This motivates the incorporation of a Fourier-domain loss function, capturing frequency-domain consistency, alongside a spectral structure consistency loss that reinforces learning stability under perturbations. Our simulation results demonstrate that CANet outperforms benchmark models across a wide range of signal-to-noise ratio (SNR) levels.
format Preprint
id arxiv_https___arxiv_org_abs_2507_04435
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Context-Aware Deep Learning for Robust Channel Extrapolation in Fluid Antenna Systems
Jin, Yanliang
Yu, Runze
Gao, Yuan
Liu, Shengli
Chu, Xiaoli
Wong, Kai-Kit
Chae, Chan-Byoung
Signal Processing
Fluid antenna systems (FAS) offer remarkable spatial flexibility but face significant challenges in acquiring high-resolution channel state information (CSI), leading to considerable overhead. To address this issue, we propose CANet, a robust deep learning model for channel extrapolation in FAS. CANet combines context-adaptive modeling with a cross-scale attention mechanism and is built on a ConvNeXt v2 backbone to improve extrapolation accuracy for unobserved antenna ports. To further enhance robustness, we introduce a novel spatial amplitude perturbation strategy, inspired by frequency-domain augmentation techniques in image processing. This motivates the incorporation of a Fourier-domain loss function, capturing frequency-domain consistency, alongside a spectral structure consistency loss that reinforces learning stability under perturbations. Our simulation results demonstrate that CANet outperforms benchmark models across a wide range of signal-to-noise ratio (SNR) levels.
title Context-Aware Deep Learning for Robust Channel Extrapolation in Fluid Antenna Systems
topic Signal Processing
url https://arxiv.org/abs/2507.04435