A gradient-inspired graph neural network with two projection modules learns holographic MIMO beamformers, achieving higher spectral efficiency than alternating optimization with much lower inference latency.
Multidimensional graph neural networks for wireless communications,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SP 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning-based Multiuser Beamforming for Holographic MIMO~Systems
A gradient-inspired graph neural network with two projection modules learns holographic MIMO beamformers, achieving higher spectral efficiency than alternating optimization with much lower inference latency.