# Knowledge-driven Meta-learning for CSI Feedback

arXiv: https://arxiv.org/abs/2310.15548 · HTML: https://mlsanity.com/paper/2310.15548/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Oct 2023.

## Built on by (most cited first, 4 of 4)

- [Channel Modeling Aided Dataset Generation for AI-Enabled CSI Feedback: Advances, Challenges, and Solutions](https://mlsanity.com/paper/2407.00896/) (2024)
- [Hierarchical ML Codebook Design for Extreme MIMO Beam Management](https://mlsanity.com/paper/2312.02178/) (2023)
- [Neural Codebook Design for Network Beam Management](https://mlsanity.com/paper/2403.03053/) (2024)
- [Uplink Assisted Joint Channel Estimation and CSI Feedback: An Approach Based on Deep Joint Source-Channel Coding](https://mlsanity.com/paper/2504.10836/) (2025)

## Abstract (arXiv)

Accurate and effective channel state information (CSI) feedback is a key technology for massive multiple-input and multiple-output systems. Recently, deep learning (DL) has been introduced for CSI feedback enhancement through massive collected training data and lengthy training time, which is quite costly and impractical for realistic deployment. In this article, a knowledge-driven meta-learning approach is proposed, where the DL model initialized by the meta model obtained from meta training phase is able to achieve rapid convergence when facing a new scenario during target retraining phase. Specifically, instead of training with massive data collected from various scenarios, the meta task environment is constructed based on the intrinsic knowledge of spatial-frequency characteristics of CSI for meta training. Moreover, the target task dataset is also augmented by exploiting the knowledge of statistical characteristics of wireless channel, so that the DL model can achieve higher performance with small actually collected dataset and short training time. In addition, we provide analyses of rationale for the improvement yielded by the knowledge in both phases. Simulation results demonstrate the superiority of the proposed approach from the perspective of feedback performance and convergence speed.