M4GN: Mesh-based Multi-segment Hierarchical Graph Network for Dynamic Simulations

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Lei, Bo, Castillo, Victor M., Hu, Yeping
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912585408839680
author Lei, Bo
Castillo, Victor M.
Hu, Yeping
author_facet Lei, Bo
Castillo, Victor M.
Hu, Yeping
contents Mesh-based graph neural networks (GNNs) have become effective surrogates for PDE simulations, yet their deep message passing incurs high cost and over-smoothing on large, long-range meshes; hierarchical GNNs shorten propagation paths but still face two key obstacles: (i) building coarse graphs that respect mesh topology, geometry, and physical discontinuities, and (ii) maintaining fine-scale accuracy without sacrificing the speed gained from coarsening. We tackle these challenges with M4GN, a three-tier, segment-centric hierarchical network. M4GN begins with a hybrid segmentation strategy that pairs a fast graph partitioner with a superpixel-style refinement guided by modal-decomposition features, producing contiguous segments of dynamically consistent nodes. These segments are encoded by a permutation-invariant aggregator, avoiding the order sensitivity and quadratic cost of aggregation approaches used in prior works. The resulting information bridges a micro-level GNN, which captures local dynamics, and a macro-level transformer that reasons efficiently across segments, achieving a principled balance between accuracy and efficiency. Evaluated on multiple representative benchmark datasets, M4GN improves prediction accuracy by up to 56% while achieving up to 22% faster inference than state-of-the-art baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2509_10659
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle M4GN: Mesh-based Multi-segment Hierarchical Graph Network for Dynamic Simulations
Lei, Bo
Castillo, Victor M.
Hu, Yeping
Machine Learning
Computational Engineering, Finance, and Science
Computational Physics
Mesh-based graph neural networks (GNNs) have become effective surrogates for PDE simulations, yet their deep message passing incurs high cost and over-smoothing on large, long-range meshes; hierarchical GNNs shorten propagation paths but still face two key obstacles: (i) building coarse graphs that respect mesh topology, geometry, and physical discontinuities, and (ii) maintaining fine-scale accuracy without sacrificing the speed gained from coarsening. We tackle these challenges with M4GN, a three-tier, segment-centric hierarchical network. M4GN begins with a hybrid segmentation strategy that pairs a fast graph partitioner with a superpixel-style refinement guided by modal-decomposition features, producing contiguous segments of dynamically consistent nodes. These segments are encoded by a permutation-invariant aggregator, avoiding the order sensitivity and quadratic cost of aggregation approaches used in prior works. The resulting information bridges a micro-level GNN, which captures local dynamics, and a macro-level transformer that reasons efficiently across segments, achieving a principled balance between accuracy and efficiency. Evaluated on multiple representative benchmark datasets, M4GN improves prediction accuracy by up to 56% while achieving up to 22% faster inference than state-of-the-art baselines.
title M4GN: Mesh-based Multi-segment Hierarchical Graph Network for Dynamic Simulations
topic Machine Learning
Computational Engineering, Finance, and Science
Computational Physics
url https://arxiv.org/abs/2509.10659