WiFo-CF: Wireless Foundation Model for CSI Feedback
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913978638139392 |
|---|---|
| author | Liu, Xuanyu Gao, Shijian Liu, Boxun Cheng, Xiang Yang, Liuqing |
| author_facet | Liu, Xuanyu Gao, Shijian Liu, Boxun Cheng, Xiang Yang, Liuqing |
| contents | Deep learning-based channel state information (CSI) feedback schemes demonstrate strong compression capabilities but are typically constrained to fixed system configurations, limiting their generalization and flexibility. To address this challenge, WiFo-CF, a novel wireless foundation model tailored for CSI feedback, is proposed, uniquely accommodating heterogeneous configurations such as varying channel dimensions, feedback rates, and data distributions within a unified framework through its key innovations: (1) a multi-user, multi-rate self-supervised pre-training strategy; and (2) a Mixture of Shared and Routed Expert (S-R MoE) architecture. Supporting the large-scale pre-training of WiFo-CF is the first heterogeneous channel feedback dataset, whose diverse patterns enable the model to achieve superior performance on both in-distribution and out-of-distribution data across simulated and real-world scenarios. Furthermore, the learned representations effectively facilitate adaptation to downstream tasks such as CSI-based indoor localization, validating WiFo-CF's scalability and deployment potential. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_04068 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | WiFo-CF: Wireless Foundation Model for CSI Feedback Liu, Xuanyu Gao, Shijian Liu, Boxun Cheng, Xiang Yang, Liuqing Signal Processing Deep learning-based channel state information (CSI) feedback schemes demonstrate strong compression capabilities but are typically constrained to fixed system configurations, limiting their generalization and flexibility. To address this challenge, WiFo-CF, a novel wireless foundation model tailored for CSI feedback, is proposed, uniquely accommodating heterogeneous configurations such as varying channel dimensions, feedback rates, and data distributions within a unified framework through its key innovations: (1) a multi-user, multi-rate self-supervised pre-training strategy; and (2) a Mixture of Shared and Routed Expert (S-R MoE) architecture. Supporting the large-scale pre-training of WiFo-CF is the first heterogeneous channel feedback dataset, whose diverse patterns enable the model to achieve superior performance on both in-distribution and out-of-distribution data across simulated and real-world scenarios. Furthermore, the learned representations effectively facilitate adaptation to downstream tasks such as CSI-based indoor localization, validating WiFo-CF's scalability and deployment potential. |
| title | WiFo-CF: Wireless Foundation Model for CSI Feedback |
| topic | Signal Processing |
| url | https://arxiv.org/abs/2508.04068 |