SPA-MAE: A Physics-Guided CSI Foundation Model for Wireless Physical Layer

TL;DR

SPA-MAE is a physics-guided foundation model for wireless communication that leverages channel knowledge and a masked autoencoder backbone to improve generalization across tasks.

Contribution

It introduces a physics-guided pretraining approach using a physical prior module to enhance wireless foundation models with limited data and low-SNR robustness.

Findings

Outperforms state-of-the-art CSI foundation models

Requires fewer parameters for comparable performance

Excels under low-SNR and limited-data scenarios

Abstract

Deep learning (DL) has been widely used in future 6G physical layer communications, but task-specific DL models are difficult to generalize across different physical layer tasks. Recently emerging wireless foundation models demonstrate strong generalization capability. However, existing methods mainly adapt pretrained language/vision models or rely on CSI reconstruction objectives for pretraining, with limited use of channel knowledge, and thus have limited performance. To address this limitation, we propose SPA-MAE, a physics-guided wireless foundation model by exploiting the adapted MAE backbone and channel knowledge. A physical prior module is developed to provide two complementary guidance signals in the pretraining stage. Specifically, the parameter-aware guidance branch extracts features from explicit multipath parameters and encourages the encoder output to align them, while the structure-aware guidance branch encourages the encoder to capture the sparse transformed-domain CSI structure obtained after a 2D FFT. After end-to-end learning, the MAE encoder will be retained for downstream tasks. Experiments on four wireless tasks show that SPA-MAE outperforms state-of-the-art CSI foundation models with smaller number of parameters, especially under low-SNR and limited-data conditions.