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

TL;DR

This paper introduces CANet, a deep learning model that improves channel extrapolation accuracy in fluid antenna systems by leveraging context-aware features, attention mechanisms, and novel augmentation strategies, reducing overhead and enhancing robustness.

Contribution

The paper presents a novel deep learning framework, CANet, combining context-adaptive modeling, cross-scale attention, and Fourier-based augmentation for robust channel extrapolation in FAS.

Findings

CANet outperforms benchmark models across various SNR levels.

The Fourier-domain loss enhances frequency consistency in extrapolation.

Spatial amplitude perturbation improves model robustness.

Abstract

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.