A graph-attention-based multimodal VAE achieves competitive reconstruction and generation of structural and functional MRI features while being more computationally efficient than diffusion-based alternatives.
The fMRI modality is represented using sFNC matri- ces, while the sMRI modality is represented as a vector of GMV features
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Latent graph encoding of multimodal neuroimaging features with generative AI architectures
A graph-attention-based multimodal VAE achieves competitive reconstruction and generation of structural and functional MRI features while being more computationally efficient than diffusion-based alternatives.