Residual Cross-Attention Transformer-Based Multi-User CSI Feedback with Deep Joint Source-Channel Coding

TL;DR

This paper introduces a deep learning-based multi-user CSI feedback framework using residual cross-attention transformers and joint source-channel coding to enhance accuracy, reduce overhead, and improve scalability in massive MIMO systems.

Contribution

It presents a novel residual cross-attention transformer architecture combined with deep joint source-channel coding for multi-user CSI feedback, addressing feedback overhead and robustness issues.

Findings

Outperforms existing methods in CSI feedback accuracy

Reduces feedback overhead through user correlation exploitation

Demonstrates robustness against uplink noise variations

Abstract

This letter proposes a deep-learning (DL)-based multi-user channel state information (CSI) feedback framework for massive multiple-input multiple-output systems, where the deep joint source-channel coding (DJSCC) is utilized to improve the CSI reconstruction accuracy. Specifically, we design a multi-user joint CSI feedback framework, whereby the CSI correlation of nearby users is utilized to reduce the feedback overhead. Under the framework, we propose a new residual cross-attention transformer architecture, which is deployed at the base station to further improve the CSI feedback performance. Moreover, to tackle the "cliff-effect" of conventional bit-level CSI feedback approaches, we integrated DJSCC into the multi-user CSI feedback, together with utilizing a two-stage training scheme to adapt to varying uplink noise levels. Experimental results demonstrate the superiority of our methods in CSI feedback performance, with low network complexity and better scalability.