HELENA: High-Efficiency Learning-based channel Estimation using dual Neural Attention

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Botero, Miguel Camelo, Beyazit, Esra Aycan, Slamnik-Kriještorac, Nina, Marquez-Barja, Johann M.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908968613314560
author Botero, Miguel Camelo
Beyazit, Esra Aycan
Slamnik-Kriještorac, Nina
Marquez-Barja, Johann M.
author_facet Botero, Miguel Camelo
Beyazit, Esra Aycan
Slamnik-Kriještorac, Nina
Marquez-Barja, Johann M.
contents Accurate channel estimation is critical for high-performance Orthogonal Frequency-Division Multiplexing systems such as 5G New Radio, particularly under low signal-to-noise ratio and stringent latency constraints. This letter presents HELENA, a compact deep learning model that combines a lightweight convolutional backbone with two efficient attention mechanisms: patch-wise multi-head self-attention for capturing global dependencies and a squeeze-and-excitation block for local feature refinement. Compared to CEViT, a state-of-the-art vision transformer-based estimator, HELENA reduces inference time by 45.0\% (0.175\,ms vs.\ 0.318\,ms), achieves comparable accuracy ($-16.78$\,dB vs.\ $-17.30$\,dB), and requires $8\times$ fewer parameters (0.11M vs.\ 0.88M), demonstrating its suitability for low-latency, real-time deployment.
format Preprint
id arxiv_https___arxiv_org_abs_2506_13408
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HELENA: High-Efficiency Learning-based channel Estimation using dual Neural Attention
Botero, Miguel Camelo
Beyazit, Esra Aycan
Slamnik-Kriještorac, Nina
Marquez-Barja, Johann M.
Signal Processing
Machine Learning
Networking and Internet Architecture
Accurate channel estimation is critical for high-performance Orthogonal Frequency-Division Multiplexing systems such as 5G New Radio, particularly under low signal-to-noise ratio and stringent latency constraints. This letter presents HELENA, a compact deep learning model that combines a lightweight convolutional backbone with two efficient attention mechanisms: patch-wise multi-head self-attention for capturing global dependencies and a squeeze-and-excitation block for local feature refinement. Compared to CEViT, a state-of-the-art vision transformer-based estimator, HELENA reduces inference time by 45.0\% (0.175\,ms vs.\ 0.318\,ms), achieves comparable accuracy ($-16.78$\,dB vs.\ $-17.30$\,dB), and requires $8\times$ fewer parameters (0.11M vs.\ 0.88M), demonstrating its suitability for low-latency, real-time deployment.
title HELENA: High-Efficiency Learning-based channel Estimation using dual Neural Attention
topic Signal Processing
Machine Learning
Networking and Internet Architecture
url https://arxiv.org/abs/2506.13408