Multi-scale physical representations for approximating pde solutions with graph neural operators - Archive ouverte HAL Access content directly
Conference Papers Year : 2022

Multi-scale physical representations for approximating pde solutions with graph neural operators

Abstract

Representing physical signals at different scales is among the most challenging problems in engineering. Several multi-scale modeling tools have been developed to describe physical systems governed by Partial Differential Equations (PDEs). These tools are at the crossroad of principled physical models and numerical schema. Recently, data-driven models have been introduced to speed-up the approximation of PDE solutions compared to numerical solvers. Among these recent data-driven methods, neural integral operators are a class that learn a mapping between function spaces. These functions are discretized on graphs (meshes) which are appropriate for modeling interactions in physical phenomena. In this work, we study three multi-resolution schema with integral kernel operators that can be approximated with Message Passing Graph Neural Networks (MPGNNs). To validate our study, we make extensive MPGNNs experiments with well-chosen metrics considering steady and unsteady PDEs.
Fichier principal
Vignette du fichier
multi_scale_physical_represent.pdf (335.74 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03709247 , version 1 (29-06-2022)

Identifiers

  • HAL Id : hal-03709247 , version 1

Cite

Leon Migus, Yuan Yin, Jocelyn Ahmed Mazari, Patrick Gallinari. Multi-scale physical representations for approximating pde solutions with graph neural operators. ICLR 2022 Workshop on Geometrical and Topological Representation Learning, Apr 2022, En ligne, France. ⟨hal-03709247⟩
62 View
192 Download

Share

Gmail Mastodon Facebook X LinkedIn More