WiFo-E: A Scalable Wireless Foundation Model for End-to-End FDD Precoding in Communication Networks
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917203324960768 |
|---|---|
| author | Wen, Weibo Gao, Shijian Zhang, Haotian Cheng, Xiang Yang, Liuqing |
| author_facet | Wen, Weibo Gao, Shijian Zhang, Haotian Cheng, Xiang Yang, Liuqing |
| contents | Accurate precoding in massive multiple-input multiple-output (MIMO) frequency-division duplexing (FDD) systems relies on efficient channel state information (CSI) acquisition. End-to-end learning frameworks improve performance by jointly optimizing this process, but they lack scalability and fail to generalize across different system configurations, such as varying numbers of antennas and users. To overcome this limitation, we introduce WiFo-E, a wireless foundation model designed for scalable end-to-end precoding. WiFo-E employs multi-task pretraining on a diverse set of configurations to learn transferable representations of underlying wireless principles. Central to the model is a sparse Mixture-of-Experts (MoE) Transformer architecture, which mitigates task interference and enhances training efficiency by activating specialized parameter subsets adaptively. Extensive simulations demonstrate that WiFo-E outperforms conventional per-configuration training and shows strong generalization to unseen system configurations, providing a flexible and efficient foundation for adaptive massive MIMO precoding. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_09186 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | WiFo-E: A Scalable Wireless Foundation Model for End-to-End FDD Precoding in Communication Networks Wen, Weibo Gao, Shijian Zhang, Haotian Cheng, Xiang Yang, Liuqing Signal Processing Accurate precoding in massive multiple-input multiple-output (MIMO) frequency-division duplexing (FDD) systems relies on efficient channel state information (CSI) acquisition. End-to-end learning frameworks improve performance by jointly optimizing this process, but they lack scalability and fail to generalize across different system configurations, such as varying numbers of antennas and users. To overcome this limitation, we introduce WiFo-E, a wireless foundation model designed for scalable end-to-end precoding. WiFo-E employs multi-task pretraining on a diverse set of configurations to learn transferable representations of underlying wireless principles. Central to the model is a sparse Mixture-of-Experts (MoE) Transformer architecture, which mitigates task interference and enhances training efficiency by activating specialized parameter subsets adaptively. Extensive simulations demonstrate that WiFo-E outperforms conventional per-configuration training and shows strong generalization to unseen system configurations, providing a flexible and efficient foundation for adaptive massive MIMO precoding. |
| title | WiFo-E: A Scalable Wireless Foundation Model for End-to-End FDD Precoding in Communication Networks |
| topic | Signal Processing |
| url | https://arxiv.org/abs/2601.09186 |