RIGNO: A Graph-Based Framework for Robust and Accurate Operator Learning for PDEs on Arbitrary Domains
Abstract
Learning the solution operators of PDEs on arbitrary domains is challenging due to the diversity of possible domain shapes, in addition to the often intricate underlying physics. We propose an end-to-end graph neural network (GNN) based neural operator to learn PDE solution operators from data on point clouds in arbitrary domains. Our multi-scale model maps data between input/output point clouds by passing it through a downsampled regional mesh. The approach includes novel elements aimed at ensuring spatio-temporal resolution invariance. Our model, termed RIGNO, is tested on a challenging suite of benchmarks composed of various time-dependent and steady PDEs defined on a diverse set of domains. We demonstrate that RIGNO is significantly more accurate than neural operator baselines and robustly generalizes to unseen resolutions both in space and in time. Our code is publicly available at github.com/camlab-ethz/rigno.
Cite
Text
Mousavi et al. "RIGNO: A Graph-Based Framework for Robust and Accurate Operator Learning for PDEs on Arbitrary Domains." Advances in Neural Information Processing Systems, 2025.Markdown
[Mousavi et al. "RIGNO: A Graph-Based Framework for Robust and Accurate Operator Learning for PDEs on Arbitrary Domains." Advances in Neural Information Processing Systems, 2025.](https://mlanthology.org/neurips/2025/mousavi2025neurips-rigno/)BibTeX
@inproceedings{mousavi2025neurips-rigno,
title = {{RIGNO: A Graph-Based Framework for Robust and Accurate Operator Learning for PDEs on Arbitrary Domains}},
author = {Mousavi, Sepehr and Wen, Shizheng and Lingsch, Levi and Herde, Maximilian and Raonic, Bogdan and Mishra, Siddhartha},
booktitle = {Advances in Neural Information Processing Systems},
year = {2025},
url = {https://mlanthology.org/neurips/2025/mousavi2025neurips-rigno/}
}