Active Learning for Neural PDE Solvers - Archive ouverte HAL
Pré-Publication, Document De Travail Année : 2024

Active Learning for Neural PDE Solvers

Résumé

Solving partial differential equations (PDEs) is a fundamental problem in engineering and science. While neural PDE solvers can be more efficient than established numerical solvers, they often require large amounts of training data that is costly to obtain. Active Learning (AL) could help surrogate models reach the same accuracy with smaller training sets by querying classical solvers with more informative initial conditions and PDE parameters. While AL is more common in other domains, it has yet to be studied extensively for neural PDE solvers. To bridge this gap, we introduce AL4PDE, a modular and extensible active learning benchmark. It provides multiple parametric PDEs and state-of-the-art surrogate models for the solver-in-the-loop setting, enabling the evaluation of existing and the development of new AL methods for PDE solving. We use the benchmark to evaluate batch active learning algorithms such as uncertainty- and feature-based methods. We show that AL reduces the average error by up to 71% compared to random sampling and significantly reduces worst-case errors. Moreover, AL generates similar datasets across repeated runs, with consistent distributions over the PDE parameters and initial conditions. The acquired datasets are reusable, providing benefits for surrogate models not involved in the data generation.
Fichier principal
Vignette du fichier
Active Learning for Neural PDE Solvers.pdf (5.41 Mo) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte
Licence

Dates et versions

hal-04707402 , version 1 (24-09-2024)

Licence

Identifiants

Citer

Daniel Musekamp, Marimuthu Kalimuthu, David Holzmüller, Makoto Takamoto, Mathias Niepert. Active Learning for Neural PDE Solvers. 2024. ⟨hal-04707402⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

More