Precoding-Oriented CSI Feedback Design with Mutual Information Regularized VQ-VAE

TL;DR

This paper introduces a novel precoding-oriented CSI feedback method using a VQ-VAE with mutual information regularization, improving feedback efficiency and channel representation in massive MIMO systems.

Contribution

It proposes a mutual information regularized VQ-VAE framework for CSI feedback, enhancing codebook utilization and interpretability under fixed feedback constraints.

Findings

Achieves downlink rates comparable to variable-length neural compression schemes.

Learned codewords are more uniformly used and interpretable.

Operates effectively with fixed-length feedback.

Abstract

Efficient channel state information (CSI) compression at the user equipment plays a key role in enabling accurate channel reconstruction and precoder design in massive multiple-input multiple-output systems. A key challenge lies in balancing the CSI feedback overhead with the achievable downlink rate, i.e., maximizing the utility of limited feedback to maintain high system performance. In this work, we propose a precoding-oriented CSI feedback framework based on a vector quantized variational autoencoder, augmented with an information-theoretic regularization. To achieve this, we introduce a differentiable mutual information lower-bound estimator as a training regularizer to promote effective utilization of the learned codebook under a fixed feedback budget. Numerical results demonstrate that the proposed method achieves rates comparable to variable-length neural compression schemes, while operating with fixed-length feedback. Furthermore, the learned codewords exhibit significantly more uniform usage and capture interpretable structures that are strongly correlated with the underlying channel state information.