Saved in:
Bibliographic Details
Main Authors: Perez-Adan, Darian, Gonzalez-Coma, Jose P., Lopez-Martinez, F. Javier, Castedo, Luis
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.04589
Tags: Add Tag
No Tags, Be the first to tag this record!
_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