DGNN: A Neural PDE Solver Induced by Discontinuous Galerkin Methods
2025-03-13Code Available0· sign in to hype
GuanYu Chen, Shengze Xu, Dong Ni, Tieyong Zeng
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/cgymmy/DGNetOfficialIn paperpytorch★ 4
- github.com/cgymmy/DGNNOfficialpytorch★ 4
Abstract
We propose a general framework for the Discontinuous Galerkin-induced Neural Network (DGNN), inspired by the Interior Penalty Discontinuous Galerkin Method (IPDGM). In this approach, the trial space consists of piecewise neural network space defined over the computational domain, while the test function space is composed of piecewise polynomials. We demonstrate the advantages of DGNN in terms of accuracy and training efficiency across several numerical examples, including stationary and time-dependent problems. Specifically, DGNN easily handles high perturbations, discontinuous solutions, and complex geometric domains.