REVIEW 18 cited by
Message Passing Neural PDE Solvers
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
The numerical solution of partial differential equations (PDEs) is difficult, having led to a century of research so far. Recently, there have been pushes to build neural--numerical hybrid solvers, which piggy-backs the modern trend towards fully end-to-end learned systems. Most works so far can only generalize over a subset of properties to which a generic solver would be faced, including: resolution, topology, geometry, boundary conditions, domain discretization regularity, dimensionality, etc. In this work, we build a solver, satisfying these properties, where all the components are based on neural message passing, replacing all heuristically designed components in the computation graph with backprop-optimized neural function approximators. We show that neural message passing solvers representationally contain some classical methods, such as finite differences, finite volumes, and WENO schemes. In order to encourage stability in training autoregressive models, we put forward a method that is based on the principle of zero-stability, posing stability as a domain adaptation problem. We validate our method on various fluid-like flow problems, demonstrating fast, stable, and accurate performance across different domain topologies, equation parameters, discretizations, etc., in 1D and 2D.
Forward citations
Cited by 18 Pith papers
-
An Energy Stable Approach for Learning Derivative Operators from Noisy Data for Maxwells Equations
SP-ADMM learns energy-stable derivative stencils for Maxwell equations from noisy data by enforcing skew-adjointness through reduced parameterization of periodic convolution stencils.
-
No Free Lunch in Flow Surrogates under Time-Varying Boundary Conditions: A Two-Regime Study
No single flow-surrogate architecture transfers from a boundary-driven Stokes film to a self-sustained Kármán wake; time treatment decides the winner and pointwise RMSE ranks the wrong models.
-
Neptuna: A Comprehensive Machine Learning Framework for Benchmarking Complex Multiphase Flows
A new 2.4 TB benchmark shows no single ML surrogate dominates on shock-driven multiphase flows, and composite losses with SoftAdapt weighting improve interface and spectral fidelity.
-
Label-Free Finite-Volume-Residual Training of Attention Graph Neural Networks for Coupled Thermo-Fluid Fields
An attention graph neural network trained only against finite-volume residuals predicts coupled 3D thermo-fluid fields without labeled CFD data, matching or beating a supervised baseline on four benchmarks.
-
Adaptive Physics Transformer with Fused Global-Local Attention for Subsurface Energy Systems
APT, a mesh-agnostic neural operator fusing graph-based local features with global attention, is claimed to be the first architecture trained directly on adaptive-mesh-refinement simulations and outperforms state-of-t...
-
FluxNet: Learning Capacity-Constrained Local Transport Operators for Conservative and Bounded PDE Surrogates
FluxNet is a family of neural PDE time-steppers whose learned transport plans make discrete conservation exact and one-sided bound preservation structural, with empirical dual-bound control via a consistency-regulariz...
-
Learning collision operators from plasma phase space data using differentiable simulators
A differentiable Fokker-Planck simulator learns advection and diffusion coefficients from PIC phase-space subpopulations, matching theory and outperforming particle-track estimates.
-
On the under-reaching phenomenon in message-passing neural PDE solvers: revisiting the CFL condition
Graph neural network PDE solvers require at least a CFL-like number of message passes for hyperbolic problems and domain-spanning passes for parabolic and elliptic problems.
-
Hierarchical Implicit Neural Emulators
Feeding a hierarchy of predicted coarse-grained future states into an autoregressive neural emulator greatly improves long-term stability for 2D turbulent flow forecasting.
-
Hybrid Neural-MPM for Interactive Fluid Simulations in Real-Time
A hybrid neural-MPM solver with a chaos-triggered fallback and a diffusion-based sketch controller enables real-time interactive fluid simulation with user control.
-
Governing Equation Discovery from Data Based on Differential Invariants
PDE discovery guided by symmetry can be done by building the SINDy library from the differential invariants of the PDE's symmetry group, which shrinks the search space and improves success rates.
-
Neural operator preconditioning from mixed dataset for the Helmholtz equations: Application to transcranial ultrasound
Six mixed training datasets are compared for a U-Net Helmholtz preconditioner; the best mix lets FGMRES solve 512×512 head-CT problems that GMRES and the Stanziola learned optimizer cannot.
-
A robust and stable hybrid neural network/finite element method for 2D flows that generalizes to different geometries
Replay training on the DNN-MG's own perturbed trajectories removes the long-time instability of the hybrid Navier-Stokes solver, while Transformers or larger patches improve accuracy on unseen geometries.
-
Accelerating HEC-RAS: A Recurrent Neural Operator for Rapid River Forecasting
An autoregressive GRU-GeoFNO model predicts HEC-RAS stage and flow on 67 Mississippi reaches with a 3.45x speedup and a median absolute stage error of 0.31 feet on a year-long hold-out.
-
GITO: Graph-Informed Transformer Operator for Learning Complex Partial Differential Equations
GITO, a graph-informed transformer operator, reports lower relative L2 errors than existing transformer-based neural operators on Navier-Stokes, heat conduction, and airfoil benchmark datasets.
-
A Deep Learning approach for parametrized and time dependent Partial Differential Equations using Dimensionality Reduction and Neural ODEs
An autoencoder plus latent neural ODE, trained with teacher forcing and autoregressive rollouts, beats several published neural PDE surrogates on benchmark equations while using fewer parameters and faster inference.
-
Separated-Variable Spectral Neural Networks: A Physics-Informed Learning Approach for High-Frequency PDEs
A separable Fourier-feature neural network with learnable frequencies and a three-level frequency sampler is reported to solve high-frequency PDEs with far fewer parameters than vanilla PINNs.
-
Principled Approaches for Extending Neural Architectures to Function Spaces for Operator Learning
A practical recipe to convert common neural architectures into discretization-agnostic neural operators, validated by Navier-Stokes experiments showing cross-resolution generalization of FNO-style models.
Discussion (0). Continue with ORCID to comment.