SPLGNIJun 16, 2025

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

arXiv:2506.13408v12 citationsh-index: 10Has Code
Originality Incremental advance
AI Analysis

This work addresses efficient channel estimation for 5G deployment, offering incremental improvements in speed and model size.

The paper tackles channel estimation for 5G systems by proposing HELENA, a compact deep learning model that reduces inference time by 45.0% and parameters by 8x while maintaining comparable accuracy to a state-of-the-art method.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes