mlsanityData to 14 Oct 2026

HI-MeshGraphNets: Efficient and Accurate Mesh-based Physics Learning with Hierarchical Multi-scale Graph Neural Networks

arXiv 2608.13827 ↗First posted 13 Aug 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Machine-learned physical surrogate models have become promising alternatives to mesh-based numerical solvers. Among them, graph neural networks (GNNs) are well suited for representing simulation meshes and learning nodal state evolution through message passing. However, conventional flat message passing becomes inefficient on large, high-fidelity meshes because information propagates only one hop per layer, requiring deep processors for long-range interactions and increasing computational cost, memory usage, and the risk of over-smoothing. To address this limitation, we propose Hierarchical Interpolating MeshGraphNets (HI-MGN), a multiscale extension of MeshGraphNets for efficient long-range communication on unstructured meshes. HI-MGN replaces the flat processor with a hierarchical multiscale processor that coarsens graphs using farthest-point sampling and Voronoi partitioning while preserving the original mesh topology. Message passing on coarse graphs enables information to travel over larger geometric distances with fewer layers, and a learned graph interpolation network reconstructs fine-resolution features. Across three structural and fluid benchmarks, HI-MGN achieves improved accuracy compared with MeshGraphNets and the Bi-Stride Multi-Scale GNN while reducing training time and peak memory usage. The results show that topology-aware hierarchical message passing and learned coarse-to-fine interpolation provide an effective and practical framework for scalable mesh-based physics surrogate modeling.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 26 of its 45 references that are in the map. First posted on arXiv 13 Aug 2026.

Builds on

26 of 45 references.

References · 26

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  3. 2019DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operatorscited by 2,018
  4. 2018Relational inductive biases, deep learning, and graph networkscited by 1,360
  5. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,102
  6. 2020Learning to Simulate Complex Physics with Graph Networkscited by 880
  7. 2020Learning Mesh-Based Simulation with Graph Networkscited by 868
  8. 2022Fourier Neural Operator with Learned Deformations for PDEs on General Geometriescited by 427
  9. 2024Transolver: A Fast Transformer Solver for PDEs on General Geometriescited by 326
  10. 2023Geometry-Informed Neural Operator for Large-Scale 3D PDEscited by 303
  11. 2018Latent-space Physics: Towards Learning the Temporal Evolution of Fluid Flowcited by 97
  12. 2025Transolver++: An Accurate Neural Solver for PDEs on Million-Scale Geometriescited by 97
14 more
  1. 2023β-Variational autoencoders and transformers for reduced-order modelling of fluid flowscited by 77
  2. 2018Deep convolutional recurrent autoencoders for learning low-dimensional feature dynamics of fluid systemscited by 54
  3. 2025AB-UPT: Scaling Neural CFD Surrogates for High-Fidelity Automotive Aerodynamics Simulations via Anchored-Branched Universal Physics Transformerscited by 53
  4. 2024Geom-DeepONet: A Point-cloud-based Deep Operator Network for Field Predictions on 3D Parameterized Geometriescited by 47
  5. 2019Multi-level Convolutional Autoencoder Networks for Parametric Prediction of Spatio-temporal Dynamicscited by 45
  6. 2022Efficient Learning of Mesh-Based Physical Simulation with BSMS-GNNcited by 45
  7. 2021Non-intrusive reduced order modeling of natural convection in porous media using convolutional autoencoders: comparison with linear subspace techniquescited by 23
  8. 2024X-MeshGraphNet: Scalable Multi-Scale Graph Neural Networks for Physics Simulationcited by 22
  9. 2026Transolver-3: Scaling Up Transformer Solvers to Industrial-Scale Geometriescited by 20
  10. 2022Physics-aware Reduced-order Modeling of Transonic Flow via β-Variational Autoencodercited by 15
  11. 2025Fusion-DeepONet: A Data-Efficient Neural Operator for Geometry-Dependent Hypersonic and Supersonic Flowscited by 13
  12. 2026MeshGraphNet-Transformer: Scalable Mesh-based Learned Simulation for Solid Mechanicscited by 10
  13. 2025PIORF: Physics-Informed Ollivier-Ricci Flow for Long-Range Interactions in Mesh Graph Neural Networkscited by 6
  14. 2023Data-driven Nonlinear Parametric Model Order Reduction Framework using Deep Hierarchical Variational Autoencodercited by 3

Built on by

Not cited yet.