An Implicit GNN Solver for Poisson-like problems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nastorg, Matthieu, Bucci, Michele Alessandro, Faney, Thibault, Gratien, Jean-Marc, Charpiat, Guillaume, Schoenauer, Marc
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913284015259648
author Nastorg, Matthieu
Bucci, Michele Alessandro
Faney, Thibault
Gratien, Jean-Marc
Charpiat, Guillaume
Schoenauer, Marc
author_facet Nastorg, Matthieu
Bucci, Michele Alessandro
Faney, Thibault
Gratien, Jean-Marc
Charpiat, Guillaume
Schoenauer, Marc
contents This paper presents $Ψ$-GNN, a novel Graph Neural Network (GNN) approach for solving the ubiquitous Poisson PDE problems with mixed boundary conditions. By leveraging the Implicit Layer Theory, $Ψ$-GNN models an "infinitely" deep network, thus avoiding the empirical tuning of the number of required Message Passing layers to attain the solution. Its original architecture explicitly takes into account the boundary conditions, a critical prerequisite for physical applications, and is able to adapt to any initially provided solution. $Ψ$-GNN is trained using a "physics-informed" loss, and the training process is stable by design, and insensitive to its initialization. Furthermore, the consistency of the approach is theoretically proven, and its flexibility and generalization efficiency are experimentally demonstrated: the same learned model can accurately handle unstructured meshes of various sizes, as well as different boundary conditions. To the best of our knowledge, $Ψ$-GNN is the first physics-informed GNN-based method that can handle various unstructured domains, boundary conditions and initial solutions while also providing convergence guarantees.
format Preprint
id arxiv_https___arxiv_org_abs_2302_10891
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle An Implicit GNN Solver for Poisson-like problems
Nastorg, Matthieu
Bucci, Michele Alessandro
Faney, Thibault
Gratien, Jean-Marc
Charpiat, Guillaume
Schoenauer, Marc
Machine Learning
Artificial Intelligence
Analysis of PDEs
This paper presents $Ψ$-GNN, a novel Graph Neural Network (GNN) approach for solving the ubiquitous Poisson PDE problems with mixed boundary conditions. By leveraging the Implicit Layer Theory, $Ψ$-GNN models an "infinitely" deep network, thus avoiding the empirical tuning of the number of required Message Passing layers to attain the solution. Its original architecture explicitly takes into account the boundary conditions, a critical prerequisite for physical applications, and is able to adapt to any initially provided solution. $Ψ$-GNN is trained using a "physics-informed" loss, and the training process is stable by design, and insensitive to its initialization. Furthermore, the consistency of the approach is theoretically proven, and its flexibility and generalization efficiency are experimentally demonstrated: the same learned model can accurately handle unstructured meshes of various sizes, as well as different boundary conditions. To the best of our knowledge, $Ψ$-GNN is the first physics-informed GNN-based method that can handle various unstructured domains, boundary conditions and initial solutions while also providing convergence guarantees.
title An Implicit GNN Solver for Poisson-like problems
topic Machine Learning
Artificial Intelligence
Analysis of PDEs
url https://arxiv.org/abs/2302.10891