English

A CSI Feedback Framework based on Transmitting the Important Values and Generating the Others

Signal Processing 2024-12-02 v2

Abstract

The application of deep learning (DL)-based channel state information (CSI) feedback frameworks in massive multiple-input multiple-output (MIMO) systems has significantly improved reconstruction accuracy. However, the limited generalization of widely adopted autoencoder-based networks for CSI feedback challenges consistent performance under dynamic wireless channel conditions and varying communication overhead constraints. To enhance the robustness of DL-based CSI feedback across diverse channel scenarios, we propose a novel framework, ITUG, where the user equipment (UE) transmits only a selected portion of critical values in the CSI matrix, while a generative model deployed at the BS reconstructs the remaining values. Specifically, we introduce a scoring algorithm to identify important values based on amplitude and contrast, an encoding algorithm to convert these values into a bit stream for transmission using adaptive bit length and a modified Huffman codebook, and a Transformer-based generative network named TPMVNet to recover the untransmitted values based on the received important values. Experimental results demonstrate that the ITUG framework, equipped with a single TPMVNet, achieves superior reconstruction performance compared to several high-performance autoencoder models across various channel conditions.

Keywords

Cite

@article{arxiv.2411.13298,
  title  = {A CSI Feedback Framework based on Transmitting the Important Values and Generating the Others},
  author = {Zhilin Du and Zhenyu Liu and Haozhen Li and Shilong Fan and Xinyu Gu and Lin Zhang},
  journal= {arXiv preprint arXiv:2411.13298},
  year   = {2024}
}

Comments

I have to make some modification on the test dataset and constrast methods in the experimental results segment

R2 v1 2026-06-28T20:06:21.974Z