CLNet: Complex Input Lightweight Neural Network Designed for Massive MIMO CSI Feedback

Abstract

The Massive Multiple Input Multiple Output (MIMO) system is a core technology of the next generation communication. With the growing complexity of CSI, CSI feedback in massive MIMO system has become a bottleneck problem. Recently, numerous deep learning-based CSI feedback approaches demonstrate their efficiency and potential. However, most existing methods improve accuracy at the cost of computational complexity by adding more advanced deep learning blocks. This letter presents a novel neural network CLNet tailored for CSI feedback problem based on the intrinsic properties of CSI. CLNet proposes a forged complex-valued input layer to process signals and utilizes spatial-attention to enhance the performance of the network. The experiment result shows that CLNet outperforms the state-of-the-art method by average accuracy improvement of 5.41% in both outdoor and indoor scenarios with average 24.1% less computational overhead. Codes are available at GitHub. <xref ref-type="fn" rid="fn1" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">¹</xref> <fn id="fn1" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><label>¹</label> <uri>https://github.com/SIJIEJI/CLNet</uri> </fn>

Topics & Concepts