Graph Neural Network Enabled Fluid Antenna Systems: A Two-Stage Approach

TL;DR

This paper introduces a two-stage graph neural network approach to optimize fluid antenna systems, enhancing performance and enabling real-time, scalable antenna position and beamforming optimization.

Contribution

It presents a novel unsupervised learning framework with a two-stage GNN for joint optimization of antenna positions and beamforming in fluid antenna systems.

Findings

Improved sum-rate and energy efficiency in FAS.

Real-time, scalable optimization demonstrated.

Two-stage GNN can operate separately.

Abstract

An emerging fluid antenna system (FAS) brings a new dimension, i.e., the antenna positions, to deal with the deep fading, but simultaneously introduces challenges related to the transmit design. This paper proposes an ``unsupervised learning to optimize" paradigm to optimize the FAS. Particularly, we formulate the sum-rate and energy efficiency (EE) maximization problems for a multiple-user multiple-input single-output (MU-MISO) FAS and solved by a two-stage graph neural network (GNN) where the first stage and the second stage are for the inference of antenna positions and beamforming vectors, respectively. The outputs of the two stages are jointly input into a unsupervised loss function to train the two-stage GNN. The numerical results demonstrates that the advantages of the FAS for performance improvement and the two-stage GNN for real-time and scalable optimization. Besides, the two stages can function separately.