REVIEW 11 cited by
Graph Neural Ordinary Differential Equations
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
We introduce the framework of continuous--depth graph neural networks (GNNs). Graph neural ordinary differential equations (GDEs) are formalized as the counterpart to GNNs where the input-output relationship is determined by a continuum of GNN layers, blending discrete topological structures and differential equations. The proposed framework is shown to be compatible with various static and autoregressive GNN models. Results prove general effectiveness of GDEs: in static settings they offer computational advantages by incorporating numerical methods in their forward pass; in dynamic settings, on the other hand, they are shown to improve performance by exploiting the geometry of the underlying dynamics.
Forward citations
Cited by 11 Pith papers
-
HyperODE: Zero-Shot Surrogate for Simulation and Inference of Dynamical Systems
A single 13k-parameter hypergraph surrogate trained on simple mass-conserving ODEs predicts calibrated trajectory quantiles and infers parameters across unseen compartmental families, system sizes, interaction orders,...
-
Spatio-Temporal Prediction of Unsteady Airfoil Aerodynamics Using Augmented Graph Neural Ordinary Differential Equations with Exogenous Controls
GNODE, a graph-neural-network-plus-neural-ODE surrogate with augmented latent dimensions, predicts unsteady transonic airfoil flows with more stable and accurate rollouts than an autoregressive GNN baseline.
-
A Stage-Aware Mixture of Experts Framework for Neurodegenerative Disease Progression Modelling
A hybrid physics-plus-neural model predicts tau PET progression better than baselines, with fitted stage weights suggesting graph spread is early and unspecified local processes are late.
-
TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows
TANGO adds a learnable energy gradient and an orthogonal tangential flow to GNN layers, improving long-range and heterophilic graph benchmarks.
-
STAGED: A Multi-Agent Neural Network for Learning Cellular Interaction Dynamics
STAGED uses agent-based graph neural ODEs to model and predict gene expression dynamics from spatial transcriptomics, recovering simulated cell-cell and gene-gene interactions in small synthetic systems.
-
GALDS: A Graph-Autoencoder-based Latent Dynamics Surrogate model to predict neurite material transport
A graph-autoencoder plus neural-ODE surrogate predicts neurite transport fields in latent space with about 3 percent mean error and up to 8 percent maximum error on unseen geometries, about 10x faster than the prior P...
-
ODeform: Learning Continuous 4D Motion for Shape Deformation with Neural ODEs
ODeform combines two parallel neural ODEs, one for rigid motion and one for local deformation, to predict arbitrary-time 3D point-cloud deformation from an initial state and physical parameters, outperforming simpler ...
-
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 traj...
-
PointODE: Lightweight Point Cloud Learning with Neural Ordinary Differential Equations on Edge
A parameter-shared residual MLP with per-point normalization reaches competitive point cloud accuracy at 0.58M parameters and runs 3.7x faster on an FPGA than the CPU baseline.
-
Graph Wave Networks
A GNN built on a wave-equation recurrence is presented, but the claimed unconditional stability is disproved by the paper's own characteristic equation.
-
Hyperbolic-PDE GNN: Spectral Graph Neural Networks in the Perspective of A System of Hyperbolic Partial Differential Equations
The paper proposes Hyperbolic-PDE GNN, a wave-equation-based message passing framework that it claims constrains node features to the Laplacian eigenbasis and improves spectral GNNs, although the supporting derivation...
Discussion (0). Continue with ORCID to comment.