Multi-Block Attention for Efficient Channel Estimation in IRS-Assisted mmWave MIMO

TL;DR

This paper introduces a deep learning framework called Multi-Block Attention (MBA) for efficient channel estimation in IRS-assisted mmWave MIMO systems, significantly reducing pilot overhead and improving estimation accuracy.

Contribution

The paper proposes a novel MBA architecture with attention-guided feature refinement and selective IRS element deactivation, achieving up to 87% reduction in pilot overhead and 51% lower NMSE.

Findings

MBA reduces pilot overhead by up to 87%.

At 10 dB SNR, MBA achieves 51% lower NMSE.

The method maintains low computational complexity.

Abstract

Intelligent Reflecting Surfaces (IRSs) are a promising technology for enhancing the spectral and energy efficiency of millimeter-wave (mmWave) multiple-input multiple-output (MIMO) systems. In these systems, accurate channel estimation remains challenging due to the passive nature of IRS elements and the high pilot overhead in large-scale deployments. This paper presents a deep learning-based Multi-Block Attention (MBA) framework for efficient cascaded channel estimation in IRS-assisted mmWave MIMO systems that utilize orthogonal frequency division multiplexing (OFDM). First, we show the optimality of the discrete Fourier transform (DFT) and Hadamard matrices as phase configurations for least squares (LS) estimation. To reduce training overhead, we selectively deactivate IRS elements and compensate for induced feature loss using a two-stage architecture: (i) a Convolutional Attention Network (CAN) for spatial correlation recovery and (ii) a Complex Multi-Convolutional Network (CMN) for noise suppression. The MBA architecture mitigates error propagation through attention-guided feature refinement and denoising. Simulation results indicate that the MBA method reduces pilot overhead by up to 87% compared to the LS estimator. Additionally, at signal-to-noise ratios of 10 dB, our proposed method achieves approximately 51% lower normalized mean squared error (NMSE) than leading methods. It also maintains low computational complexity and adapts effectively to various propagation environments.