An Implicit GNN Solver for Poisson-like problems - A&O (Apprentissage et Optimisation) Access content directly
Preprints, Working Papers, ... (Preprint) Year : 2023

An Implicit GNN Solver for Poisson-like problems

Abstract

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.
Fichier principal
Vignette du fichier
main.pdf (7.15 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03970501 , version 1 (02-02-2023)
hal-03970501 , version 2 (14-02-2023)
hal-03970501 , version 3 (21-03-2024)

Identifiers

Cite

Matthieu Nastorg, Michele Alessandro Bucci, Thibault Faney, Jean-Marc Gratien, Guillaume Charpiat, et al.. An Implicit GNN Solver for Poisson-like problems. 2023. ⟨hal-03970501v2⟩
181 View
180 Download

Altmetric

Share

Gmail Facebook X LinkedIn More