Meta Learning of Interface Conditions for Multi-Domain Physics-Informed Neural Networks

TL;DR

This paper introduces METALIC, a meta-learning approach using multi-arm bandits to dynamically select optimal interface conditions for multi-domain physics-informed neural networks solving parametric PDEs, improving performance and flexibility.

Contribution

The paper proposes a novel meta-learning method with bandit models to adaptively choose interface conditions in multi-domain PINNs, addressing a key challenge in the field.

Findings

METALIC outperforms baseline methods on four benchmark PDE families.

The bandit models effectively predict interface condition performance.

The approach demonstrates theoretical guarantees via sub-linear regret bounds.

Abstract

Physics-informed neural networks (PINNs) are emerging as popular mesh-free solvers for partial differential equations (PDEs). Recent extensions decompose the domain, apply different PINNs to solve the problem in each subdomain, and stitch the subdomains at the interface. Thereby, they can further alleviate the problem complexity, reduce the computational cost, and allow parallelization. However, the performance of multi-domain PINNs is sensitive to the choice of the interface conditions. While quite a few conditions have been proposed, there is no suggestion about how to select the conditions according to specific problems. To address this gap, we propose META Learning of Interface Conditions (METALIC), a simple, efficient yet powerful approach to dynamically determine appropriate interface conditions for solving a family of parametric PDEs. Specifically, we develop two contextual multi-arm bandit (MAB) models. The first one applies to the entire training course, and online updates a Gaussian process (GP) reward that given the PDE parameters and interface conditions predicts the performance. We prove a sub-linear regret bound for both UCB and Thompson sampling, which in theory guarantees the effectiveness of our MAB. The second one partitions the training into two stages, one is the stochastic phase and the other deterministic phase; we update a GP reward for each phase to enable different condition selections at the two stages to further bolster the flexibility and performance. We have shown the advantage of METALIC on four bench-mark PDE families.