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

2025-05-26

AI Summary

To address the high feedback overhead and low reconstruction accuracy of multi-user channel state information (CSI) in massive MIMO systems, this paper proposes a joint modeling and end-to-end optimized feedback framework. Methodologically: (1) it exploits inter-user spatial channel correlation to design a multi-user joint encoder; (2) it introduces a residual cross-attention Transformer at the base station for high-fidelity CSI reconstruction; (3) it pioneers the integration of deep joint source-channel coding (DJSCC) into multi-user CSI feedback, eliminating the “cliff effect” inherent in conventional quantized feedback; and (4) it proposes a two-stage adaptive training strategy to accommodate dynamic uplink signal-to-noise ratios (SNRs). Experimental results demonstrate that the method significantly improves reconstruction accuracy (PSNR gain of 3.2 dB), achieves low computational complexity, exhibits strong scalability, and maintains robust performance across a wide SNR range.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Multimodal Learning
• Search and Optimization: Learning to Search

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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.

Problem

• Improving CSI reconstruction accuracy using deep joint source-channel coding
• Reducing feedback overhead by leveraging multi-user CSI correlation
• Addressing cliff-effect in bit-level CSI feedback with DJSCC

Innovation

• Residual cross-attention transformer architecture improves CSI feedback
• Deep joint source-channel coding enhances reconstruction accuracy
• Two-stage training adapts to varying uplink noise levels