Up-sampling-only and Adaptive Mesh-based GNN for Simulating Physical Systems
Not on the map. Why?
Abstract (arXiv)
Traditional simulation of complex mechanical systems relies on numerical solvers of Partial Differential Equations (PDEs), e.g., using the Finite Element Method (FEM). The FEM solvers frequently suffer from intensive computation cost and high running time. Recent graph neural network (GNN)-based simulation models can improve running time meanwhile with acceptable accuracy. Unfortunately, they are hard to tailor GNNs for complex mechanical systems, including such disadvantages as ineffective representation and inefficient message propagation (MP). To tackle these issues, in this paper, with the proposed Up-sampling-only and Adaptive MP techniques, we develop a novel hierarchical Mesh Graph Network, namely UA-MGN, for efficient and effective mechanical simulation. Evaluation on two synthetic and one real datasets demonstrates the superiority of the UA-MGN. For example, on the Beam dataset, compared to the state-of-the-art MS-MGN, UA-MGN leads to 40.99% lower errors but using only 43.48% fewer network parameters and 4.49% fewer floating point operations (FLOPs).
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 27 of its 60 references that are in the map. First posted on arXiv 7 Sep 2024.
Builds on
27 of 60 references.
References · 27
- 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
- 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,806
- 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,131
- 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
- 2020Learning to Simulate Complex Physics with Graph Networkscited by 867
- 2020Learning Mesh-Based Simulation with Graph Networkscited by 840
- 2020Neural Operator: Graph Kernel Network for Partial Differential Equationscited by 722
- 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 679
- 2019Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological Viewcited by 544
- 2021Machine learning accelerated computational fluid dynamicscited by 461
- 2022Fourier Neural Operator with Learned Deformations for PDEs on General Geometriescited by 416
- 2020Multipole Graph Neural Operator for Parametric Partial Differential Equationscited by 343
15 more
- 2018Deep Learning Methods for Reynolds-Averaged Navier-Stokes Simulations of Airfoil Flowscited by 147
- 2019Learning to Optimize Multigrid PDE Solverscited by 79
- 2020A physics-informed operator regression framework for extracting data-driven continuum modelscited by 60
- 2022Geometrically Equivariant Graph Neural Networks: A Surveycited by 55
- 2021Simulating Continuum Mechanics with Multi-Scale Graph Neural Networkscited by 39
- 2022Physical Design using Differentiable Learned Simulatorscited by 37
- 2022Learning the Dynamics of Physical Systems from Sparse Observations with Finite Element Networkscited by 33
- 2020Accelerating Physics-Informed Neural Network Training with Prior Dictionariescited by 17
- 2024Multiscale graph neural networks with adaptive mesh refinement for accelerating mesh-based simulationscited by 12
- 2021Probabilistic Deep Learning for Real-Time Large Deformation Simulationscited by 11
- 2024Social Physics Informed Diffusion Model for Crowd Simulationcited by 11
- 2021Physics-Guided Discovery of Highly Nonlinear Parametric Partial Differential Equationscited by 6
- 2024MOSS: A Large-scale Open Microscopic Traffic Simulation Systemcited by 6
- 2023Structure-Aware DropEdge Towards Deep Graph Convolutional Networkscited by 3
- 2021Parallel Physics-Informed Neural Networks with Bidirectional Balancecited by 2
Built on by
Citing papers per year: 2025: 2; 2026: 1.
3 papers.