CSI Sensing and Feedback: A Semi-Supervised Learning Approach

TL;DR

This paper introduces a semi-supervised learning approach for CSI sensing and feedback in MIMO systems, enabling environment sensing and reducing labeled data requirements while improving system performance.

Contribution

It proposes the $S^2$CsiNet$ network that integrates semi-supervised learning for environment sensing and CSI feedback, addressing data labeling and environment variation challenges.

Findings

Improves CSI feedback feasibility in indoor and outdoor environments.

Reduces labeled dataset needs by up to 96.2%.

Enhances system performance through data distillation and latent information mining.

Abstract

Deep learning-based (DL-based) channel state information (CSI) feedback for a Massive multiple-input multiple-output (MIMO) system has proved to be a creative and efficient application. However, the existing systems ignored the wireless channel environment variation sensing, e.g., indoor and outdoor scenarios. Moreover, systems training requires excess pre-labeled CSI data, which is often unavailable. In this letter, to address these issues, we first exploit the rationality of introducing semi-supervised learning on CSI feedback, then one semi-supervised CSI sensing and feedback Network ($S^2$CsiNet) with three classifiers comparisons is proposed. Experiment shows that $S^2$CsiNet primarily improves the feasibility of the DL-based CSI feedback system by \textbf{\textit{indoor}} and \textbf{\textit{outdoor}} environment sensing and at most 96.2\% labeled dataset decreasing and secondarily boost the system performance by data distillation and latent information mining.