Graph Neural Ordinary Differential Equations
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.
This paper has not been read by Pith yet.
Forward citations
Cited by 19 Pith papers
-
Zero-Shot Size Transfer for Neural ODEs on Sparse Random Graphs: Graphon Limits and Adjoint Convergence
Proves O((α_n n)^{-1/2}) convergence of GNDE trajectories and adjoints to Graphon-NDE limits on sparse random graphs, with DTO/OTD consistency and experimental support for zero-shot transfer.
-
AGDN: Learning to Solve Traveling Salesman Problem with Anisotropic Graph Diffusion Network
AGDN is a new GNN framework using a MixScore matrix and anisotropic graph diffusion to outperform prior methods on TSP instances across sizes and distributions.
-
Graph Navier Stokes Networks
GNSN defines a dynamic velocity field on graphs to enable convection alongside diffusion, mitigating oversmoothing and outperforming baselines on twelve datasets with varying homophily.
-
PiGGO: Physics-Guided Learnable Graph Kalman Filters for Virtual Sensing of Nonlinear Dynamic Structures under Uncertainty
PiGGO integrates a learned graph neural ODE as the continuous-time dynamics model within an extended Kalman filter to enable online virtual sensing and uncertainty-aware state estimation for nonlinear dynamic systems ...
-
Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors
NodePFN pre-trains on synthetic graphs with controllable homophily and causal feature-label models to achieve 71.27 average accuracy on 23 node classification benchmarks without graph-specific training.
-
INDEQS: Informed Neural controlled Differential EQuationS
INDEQS is a graph-informed NCDE variant that separates inner hidden-state mixing from outer vector-field mixing and reports lower MAE than uninformed NCDEs on synthetic advection data and real river/traffic tasks when...
-
Mechanical Field Networks: Structured Neural Dynamics for Multivariate Systems
MF-Net learns a shared field state and mechanical transition rule from trajectories to deliver competitive forecasting and recoverable relation matrices on Lorenz-96 and real systems.
-
Graph Navier Stokes Networks
GNSN adds convection governed by a dynamic velocity field to graph message passing, adaptively balancing it with diffusion to handle varying homophily levels and reduce oversmoothing while outperforming baselines on 1...
-
BrainDyn: A Sheaf Neural ODE for Generative Brain Dynamics
BrainDyn is a sheaf neural ODE model that encodes brain region activity history via LSTMs, projects states through restriction maps, and uses a sheaf Laplacian for message passing to generate continuous-time dynamics ...
-
PnP-Corrector: A Universal Correction Framework for Coupled Spatiotemporal Forecasting
PnP-Corrector decouples physics simulation from error correction via a plug-and-play agent, cutting error by 29% in 300-day global ocean-atmosphere forecasts.
-
PnP-Corrector: A Universal Correction Framework for Coupled Spatiotemporal Forecasting
PnP-Corrector decouples physics simulation from error correction to counter reciprocal error amplification in coupled spatiotemporal forecasting, cutting error by 29% in a 300-day ocean-atmosphere test.
-
Continuity Laws for Sequential Models
S4 models exhibit stable time-continuity unlike sensitive S6 models, with task continuity predicting performance and enabling temporal subsampling for better efficiency.
-
Multiscale Decomposition Reveals Predictable Interannual Variability and Climate Trends in Antarctic Sea Ice Loss
Hierarchical DMD on Antarctic sea ice data attributes 2014-2017 fluctuations to interannual modes, identifies a dominant climate trend after 2022, and delivers a low-cost IceDMD predictor that outperforms existing met...
-
PDSL: Propagation Dynamics Aware Framework for Source Localization
PDSL integrates deep generative models with Graph Neural ODEs to model stochastic diffusion dynamics and improve source localization accuracy over prior topology-focused methods.
-
Multiscale Decomposition Reveals Predictable Interannual Variability and Climate Trends in Antarctic Sea Ice Loss
Hierarchical DMD decomposition of Antarctic sea ice data separates interannual variability from an emerging climate trend and supports two-year forecasts via a regularized predictive model (IceDMD) that outperforms ex...
-
Graph Neural Ordinary Differential Equations for Power System Identification
MPG-NODEs identify power system dynamics more flexibly than standard neural ODEs by using graph message passing, enabling transfer learning for adding or removing lines and units.
-
A Nonlinear Separation Principle via Contraction Theory: Applications to Neural Networks, Control, and Learning
A contraction-theory separation principle yields global exponential stability for controller-observer pairs and sharp LMI certificates for contractive RNNs, enabling stable output tracking and implicit neural network design.
-
COGENT: Continuous Graph Emulators with Neural Ordinary Differential Equations for Long-Term Physical Forecasting
COGENT is a continuous graph emulator using Neural ODEs for stable long-term forecasting on irregular geospatial meshes, evaluated on ice-sheet simulations with improved stability over autoregressive baselines.
-
PnP-Corrector: A Universal Correction Framework for Coupled Spatiotemporal Forecasting
PnP-Corrector decouples pre-trained physics engines from a correction agent to mitigate reciprocal error amplification in coupled spatiotemporal forecasting, cutting error by 28% on a 300-day ocean-atmosphere task.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.