LD-GCN couples an encoder-free latent-space neural ODE with a graph convolutional decoder, achieving accurate reduced-order modeling of time-dependent parameterized PDEs and detecting bifurcations from the latent trajectories.
hub
Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs
1 Pith paper cite this work, alongside 1,850 external citations. Polarity classification is still indexing.
1
Pith paper citing it
1,850
external citations · OpenAlex
hub tools
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Latent Dynamics Graph Convolutional Networks for model order reduction of parameterized time-dependent PDEs
LD-GCN couples an encoder-free latent-space neural ODE with a graph convolutional decoder, achieving accurate reduced-order modeling of time-dependent parameterized PDEs and detecting bifurcations from the latent trajectories.