Pretraining Codomain Attention Neural Operators for Solving Multiphysics PDEs

1 code implementation • 19 Mar 2024 • Md Ashiqur Rahman, Robert Joseph George, Mogab Elleithy, Daniel Leibovici, Zongyi Li, Boris Bonev, Colin White, Julius Berner, Raymond A. Yeh, Jean Kossaifi, Kamyar Azizzadenesheli, Anima Anandkumar

On complex downstream tasks with limited data, such as fluid flow simulations and fluid-structure interactions, we found CoDA-NO to outperform existing methods on the few-shot learning task by over $36\%$.

Few-Shot Learning Self-Supervised Learning

Fourier Continuation for Exact Derivative Computation in Physics-Informed Neural Operators

no code implementations • 29 Nov 2022 • Haydn Maust, Zongyi Li, YiXuan Wang, Daniel Leibovici, Oscar Bruno, Thomas Hou, Anima Anandkumar

The physics-informed neural operator (PINO) is a machine learning architecture that has shown promising empirical results for learning partial differential equations.