DUGC-VRNet: Joint VR Recognition and Channel Estimation for Spatially Non-Stationary XL-MIMO

2026-03-24

AI Summary

This work addresses the challenge of near-field channel estimation in extremely large-scale MIMO systems, where spatial non-stationarity—particularly the dynamically varying visibility regions causing subsets of antennas to become invisible—severely degrades performance. To tackle this issue, the authors propose a novel joint architecture that integrates a deep unfolding network (DUN) with a graph convolutional network (GCN). This is the first approach to couple GCN with DUN for channel estimation, leveraging graph-structured channel modeling to dynamically guide adaptive, visibility-aware estimation. Additionally, a weight pruning strategy is introduced to yield a lightweight model. Experimental results demonstrate that the proposed method significantly improves both channel estimation accuracy and visibility region detection under non-stationary conditions, while the pruned lightweight variant retains excellent performance.

Abstract

In this letter, we address spatially non-stationary near-field channel estimation for extremely large-scale multiple-input multiple-output (XL-MIMO) systems with a hybrid combining architecture. One key challenge in the considered problem lies in that conventional channel estimation algorithms typically struggle to effectively identify and adapt to the partial antenna visibility caused by varying visibility regions (VRs), thereby compromising estimation accuracy. To perform joint VR recognition and channel estimation, we integrate a deep unfolding network (DUN) with a graph convolution network (GCN), leading to a Deep Unfolding and Graph Convolution coupled, Visibility Region Aware Network (DUGC-VRNet). By leveraging the channel's graph structure, the GCN infers and feeds back VR information to dynamically guide the DUN's updates, thereby enhancing reliable channel estimation under spatial non-stationarity. To reduce DUGC-VRNet's complexity, we apply weight pruning to obtain a lightweight network. Simulation results demonstrate that the DUGC-VRNet and its pruned variant achieve superior channel estimation and more accurate VR recognition under spatially non-stationary conditions.

Problem

• XL-MIMO
• spatial non-stationarity
• channel estimation
• visibility regions
• near-field

Innovation

• Deep Unfolding Network
• Graph Convolution Network
• Visibility Region Recognition
• Spatially Non-Stationary Channel
• XL-MIMO