Flexible SE(2) graph neural networks with applications to PDE surrogates
Not on the map. Why?
Abstract (arXiv)
This paper presents a novel approach for constructing graph neural networks equivariant to 2D rotations and translations and leveraging them as PDE surrogates on non-gridded domains. We show that aligning the representations with the principal axis allows us to sidestep many constraints while preserving SE(2) equivariance. By applying our model as a surrogate for fluid flow simulations and conducting thorough benchmarks against non-equivariant models, we demonstrate significant gains in terms of both data efficiency and accuracy.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 25 of its 42 references that are in the map. First posted on arXiv 30 May 2024.
Builds on
25 of 42 references.
References · 25
- 2017Attention Is All You Needcited by 60,361
- 2016Layer Normalizationcited by 5,669
- 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,908
- 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
- 2020Learning to Simulate Complex Physics with Graph Networkscited by 880
- 2020Neural Operator: Graph Kernel Network for Partial Differential Equationscited by 734
- 2021Physics-informed neural networks (PINNs) for fluid mechanics: A reviewcited by 473
- 2019General E(2)-Equivariant Steerable CNNscited by 446
- 2022Message Passing Neural PDE Solverscited by 386
- 20183D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Datacited by 354
- 2016Harmonic Networks: Deep Translation and Rotation Equivariancecited by 295
- 2023EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representationscited by 204
13 more
- 2018Bayesian Deep Convolutional Encoder-Decoder Networks for Surrogate Modeling and Uncertainty Quantificationcited by 199
- 2022Towards Multi-spatiotemporal-scale Generalized PDE Modelingcited by 197
- 2022e3nn: Euclidean Neural Networkscited by 174
- 2020Combining Differentiable PDE Solvers and Graph Neural Networks for Fluid Flow Predictioncited by 138
- 2023Scalable Transformer for PDE Surrogate Modelingcited by 128
- 2023Reducing SO(3) Convolutions to SO(2) for Efficient Equivariant GNNscited by 117
- 2020Gauge Equivariant Mesh CNNs: Anisotropic convolutions on geometric graphscited by 92
- 2022Clifford Neural Layers for PDE Modelingcited by 92
- 2021Simulation Intelligence: Towards a New Generation of Scientific Methodscited by 68
- 2020Learning continuous-time PDEs from sparse data with graph neural networkscited by 53
- 2022Physics-Embedded Neural Networks: Graph Neural PDE Solvers with Mixed Boundary Conditionscited by 33
- 2023Multi-scale Time-stepping of Partial Differential Equations with Transformerscited by 14
- 2023Carbohydrate NMR chemical shift predictions using E(3) equivariant graph neural networkscited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.