Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.19849 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910236536733696 |
|---|---|
| author | Chen, Chen Jin, Weijie He, Hengtao Sun, Xiaoheng Jin, Shi |
| author_facet | Chen, Chen Jin, Weijie He, Hengtao Sun, Xiaoheng Jin, Shi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_19849 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SPA-MAE: A Physics-Guided CSI Foundation Model for Wireless Physical Layer Chen, Chen Jin, Weijie He, Hengtao Sun, Xiaoheng Jin, Shi Information Theory 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. |
| title | SPA-MAE: A Physics-Guided CSI Foundation Model for Wireless Physical Layer |
| topic | Information Theory |
| url | https://arxiv.org/abs/2605.19849 |