DJSCC-Enabled Multi-User Semantic CSI Feedback for Hybrid Beamforming in Dual-Polarized cmWave Massive MIMO

2026-05-19

AI Summary

This work addresses the high overhead and low efficiency of channel state information (CSI) feedback in 6G centimeter-wave massive MIMO-OFDM systems by proposing an end-to-end deep learning-based framework for joint semantic-level CSI feedback and beamforming optimization. The approach employs distributed user-side encoders to jointly compress dual-polarized CSI, incorporating a cross-polarization interaction module to exploit inter-polarization correlations. Robust and efficient semantic feedback is achieved by integrating the MAXIM architecture with deep joint source-channel coding (DJSCC). At the base station, the decoder directly outputs the hybrid beamforming matrix without requiring explicit CSI reconstruction. Experimental results demonstrate that, under limited feedback symbols, the proposed scheme significantly improves downlink sum rates in multi-user scenarios and consistently exhibits superior robustness and performance gains across varying signal-to-noise ratios.

Abstract

Driven by the ultra-high throughput requirements of 6G, wireless communications are migrating to centimeter wave (cmWave) bands to overcome the limitations of current spectral resources. Massive multiple-input multiple-output (MIMO) and orthogonal frequency division multiplexing (OFDM) systems aim to achieve high spectral efficiency in cmWave regimes but are often constrained by the heavy overhead of downlink channel state information (CSI) feedback. This paper proposes a deep learning scheme based on the multi-axis multi-layer perceptron for image processing (MAXIM) architecture for joint semantic CSI feedback and hybrid beamforming in multi-user cmWave MIMO-OFDM systems, which maximizes the downlink sum rate by end-to-end optimization. Specifically, distributed encoders at multiple user equipments (UEs) perform limited CSI feedback, while the decoder at the base station (BS) jointly designs the hybrid beamforming matrices without explicit CSI reconstruction. The uplink transmission is implemented via deep joint source-channel coding (DJSCC) to enhance CSI compression efficiency and noise robustness. Furthermore, considering the high correlation between vertical and horizontal polarization channels in dual-polarized massive MIMO systems, a cross-polarization interaction module is introduced at the UEs to exploit polarization correlations for joint CSI compression. Simulation results demonstrate that the proposed method improves the downlink sum rate under various signal-to-noise ratio (SNR) conditions with a limited number of feedback symbols, validating its robustness and superiority in multi-user dual-polarized cmWave MIMO-OFDM systems.

Problem

• CSI feedback
• massive MIMO
• cmWave
• hybrid beamforming
• multi-user

Innovation

• semantic CSI feedback
• hybrid beamforming
• deep joint source-channel coding (DJSCC)
• dual-polarized massive MIMO
• MAXIM architecture