CSI-GPT: Integrating Generative Pre-Trained Transformer with Federated-Tuning to Acquire Downlink Massive MIMO Channels

TL;DR

This paper introduces CSI-GPT, a novel approach combining a Swin Transformer-based network and federated-tuning to efficiently acquire downlink CSI in massive MIMO systems with low overhead and limited training data.

Contribution

It proposes a new integrated framework using GPT, Swin Transformer, and federated-tuning for downlink CSI acquisition with reduced communication overhead.

Findings

SWTCAN effectively acquires downlink CSI.

Federated-tuning reduces communication overhead.

Simulation confirms improved performance and efficiency.

Abstract

In massive multiple-input multiple-output (MIMO) systems, how to reliably acquire downlink channel state information (CSI) with low overhead is challenging. In this work, by integrating the generative pre-trained Transformer (GPT) with federated-tuning, we propose a CSI-GPT approach to realize efficient downlink CSI acquisition. Specifically, we first propose a Swin Transformer-based channel acquisition network (SWTCAN) to acquire downlink CSI, where pilot signals, downlink channel estimation, and uplink CSI feedback are jointly designed. Furthermore, to solve the problem of insufficient training data, we propose a variational auto-encoder-based channel sample generator (VAE-CSG), which can generate sufficient CSI samples based on a limited number of high-quality CSI data obtained from the current cell. The CSI dataset generated from VAE-CSG will be used for pre-training SWTCAN. To fine-tune the pre-trained SWTCAN for improved performance, we propose an online federated-tuning method, where only a small amount of SWTCAN parameters are unfrozen and updated using over-the-air computation, avoiding the high communication overhead caused by aggregating the complete CSI samples from user equipment (UEs) to the BS for centralized fine-tuning. Simulation results verify the advantages of the proposed SWTCAN and the communication efficiency of the proposed federated-tuning method. Our code is publicly available at https://github.com/BIT-ZY/CSI-GPT