Work

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

Year: 2025

Type: article

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.

Source: IEEE Wireless Communications Letters

DOI: 10.1109/lwc.2025.3574011

Authors: Hengwei Zhang, Minghui Wu, Li Qiao, Ling Liu, Ziqi Han, Zhen Gao

Institutions: Beijing Institute of Technology, Xidian University, Guangzhou Institute of Technology, Ministry of Industry and Information Technology

Language: English

Topic: Advanced Wireless Communication Techniques

Subfield: Electrical and Electronic Engineering

Field: Engineering

Domain: Physical Sciences

Open Access status: green

Funders: National Natural Science Foundation of China, Natural Science Foundation of Shandong Province, Beijing Nova Program

Awards: G6139073070, G7894506616