Learning-Based Phase Compression and Quantization for Massive MIMO CSI Feedback with Magnitude-Aided Information

In frequency-division duplexing (FDD) massive multiple-input multiple-output (MIMO) wireless systems, deep learning techniques are regarded as one of the most efficient solutions for CSI recovery. In recent times, to achieve better CSI magnitude recovery at base stations, advanced learning-based CSI feedback solutions decouple magnitude and phase recovery to fully leverage the strong correlation between current CSI magnitudes and those of previous time slots, uplink band, and near locations. However, the CSI phase recovery is a major challenge to further enhance the CSI recovery owing to its complicated patterns. In this letter, we propose a learning-based CSI feedback framework based on limited feedback and magnitude-aided information. In contrast to previous works, our proposed framework with a proposed loss function enables end-to-end learning to jointly optimize the CSI magnitude and phase recovery performance. Numerical simulations show that, the proposed loss function outperform alternate approaches for phase recovery over the overall CSI recovery in both indoor and outdoor scenarios. The performance of the proposed framework was also examined using different core layer designs.