Time-independent Partial Differential Equations (PDEs) on large meshes pose significant challenges for data-driven neural PDE solvers. We introduce a novel graph rewiring technique to tackle some of these challenges, such as aggregating information across scales and on irregular meshes. Our proposed approach bridges distant nodes, enhancing the global interaction capabilities of GNNs. Our experiments on three datasets reveal that GNN-based methods set new performance standards for time-independent PDEs on irregular meshes. Finally, we show that our graph rewiring strategy boosts the performance of baseline methods, achieving state-of-the-art results in one of the tasks.
@article{arxiv.2311.05964,
title = {Multiscale Neural Operators for Solving Time-Independent PDEs},
author = {Winfried Ripken and Lisa Coiffard and Felix Pieper and Sebastian Dziadzio},
journal= {arXiv preprint arXiv:2311.05964},
year = {2023}
}
Comments
The Symbiosis of Deep Learning and Differential Equations III @ NeurIPS 2023