Efficient Global-Local Fusion Sampling for Physics-Informed Neural Networks

TL;DR

This paper introduces a novel Global-Local Fusion Sampling strategy for PINNs that adaptively concentrates samples in difficult regions, improving accuracy and efficiency over traditional sampling methods.

Contribution

The paper proposes a residual-adaptive sampling method combined with a lightweight surrogate to enhance PINNs' training efficiency and robustness.

Findings

GLF sampling improves accuracy over global and local methods

The surrogate reduces computational cost significantly

Experiments show consistent performance gains on benchmark PDEs

Abstract

The accuracy of Physics-Informed Neural Networks (PINNs) critically depends on the placement of collocation points, as the PDE loss is approximated through sampling over the solution domain. Global sampling ensures stability by covering the entire domain but requires many samples and is computationally expensive, whereas local sampling improves efficiency by focusing on high-residual regions but may neglect well-learned areas, reducing robustness. We propose a Global-Local Fusion (GLF) Sampling Strategy that combines the strengths of both approaches. Specifically, new collocation points are generated by perturbing training points with Gaussian noise scaled inversely to the residual, thereby concentrating samples in difficult regions while preserving exploration. To further reduce computational overhead, a lightweight linear surrogate is introduced to approximate the global residual-based distribution, achieving similar effectiveness at a fraction of the cost. Together, these components, residual-adaptive sampling and residual-based approximation, preserve the stability of global methods while retaining the efficiency of local refinement. Extensive experiments on benchmark PDEs demonstrate that GLF consistently improves both accuracy and efficiency compared with global and local sampling strategies. This study provides a practical and scalable framework for enhancing the reliability and efficiency of PINNs in solving complex and high-dimensional PDEs.