Greedy and Transformer-Based Multi-Port Selection for Slow Fluid Antenna Multiple Access
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918429978525696 |
|---|---|
| author | Perez-Adan, Darian Gonzalez-Coma, Jose P. Lopez-Martinez, F. Javier Castedo, Luis |
| author_facet | Perez-Adan, Darian Gonzalez-Coma, Jose P. Lopez-Martinez, F. Javier Castedo, Luis |
| contents | We address the port-selection problem in fluid antenna multiple access (FAMA) systems with multi-port fluid antenna (FA) receivers. Existing methods either achieve near-optimal spectral efficiency (SE) at prohibitive computational cost or sacrifice significant performance for lower complexity. We propose two complementary strategies: (i) GFwd+S, a greedy forward-selection method with swap refinement that consistently outperforms state-of-the-art reference schemes in terms of SE, and (ii) a Transformer-based neural network trained via imitation learning followed by a Reinforce policy-gradient stage, which approaches GFwd+S performance at lower computational cost. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_04589 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Greedy and Transformer-Based Multi-Port Selection for Slow Fluid Antenna Multiple Access Perez-Adan, Darian Gonzalez-Coma, Jose P. Lopez-Martinez, F. Javier Castedo, Luis Artificial Intelligence Machine Learning We address the port-selection problem in fluid antenna multiple access (FAMA) systems with multi-port fluid antenna (FA) receivers. Existing methods either achieve near-optimal spectral efficiency (SE) at prohibitive computational cost or sacrifice significant performance for lower complexity. We propose two complementary strategies: (i) GFwd+S, a greedy forward-selection method with swap refinement that consistently outperforms state-of-the-art reference schemes in terms of SE, and (ii) a Transformer-based neural network trained via imitation learning followed by a Reinforce policy-gradient stage, which approaches GFwd+S performance at lower computational cost. |
| title | Greedy and Transformer-Based Multi-Port Selection for Slow Fluid Antenna Multiple Access |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2604.04589 |