轻量级神经网络提升5G信道估计速度与效率
HELENA: High-Efficiency Learning-based channel Estimation using dual Neural Attention
- 结合卷积骨干与双注意力机制，兼顾全局与局部特征
- 推理时间减少45%，参数量仅需1/8，误差仅-16.78dB
- 适合低延迟、实时部署的5G通信系统
准确的信道估计对高性能正交频分复用系统（如5G新空口）至关重要，尤其在低信噪比和严苛延迟约束下。本文提出HELENA，一种紧凑型深度学习模型，采用轻量级卷积主干网络，并融合两种高效注意力机制：用于捕捉全局依赖的块级多头自注意力，以及用于局部特征优化的挤压-激励模块。相比最先进的基于视觉变换器的估计器CEViT，HELENA将推理时间降低45.0%（0.175毫秒 vs. 0.318毫秒），实现相近精度（-16.78 dB vs. -17.30 dB），且参数量减少8倍（0.11M vs. 0.88M），证明其适用于低延迟、实时部署的无线通信系统。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。