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.
| Subjects: | Signal Processing (eess.SP); Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.15032 [eess.SP] |
| (or arXiv:2605.15032v1 [eess.SP] for this version) | |
| https://doi.org/10.48550/arXiv.2605.15032 arXiv-issued DOI via DataCite (pending registration) |
|
| Journal reference: | IEEE Transactions on Communications, vol. 73, no. 12, pp. 13891-13903, Dec. 2025 |
| Related DOI: | https://doi.org/10.1109/TCOMM.2025.3618696
DOI(s) linking to related resources |
Submission history
From: Mehrshad Momen Tayefeh [view email]
[v1]
Thu, 14 May 2026 16:27:38 UTC (4,312 KB)