Transfer Learning in Physics-Informed Neural Networks: Full Fine-Tuning, Lightweight Fine-Tuning, and Low-Rank Adaptation
This work addresses the problem of inefficient retraining in PINNs for computational physics applications, offering incremental improvements in transfer learning techniques.
The paper tackles the limitation of Physics-Informed Neural Networks (PINNs) requiring retraining for changes in problem conditions by exploring transfer learning methods, including full fine-tuning and Low-Rank Adaptation (LoRA), which significantly improve convergence speed and slightly enhance accuracy across different boundary conditions, materials, and geometries.
AI for PDEs has garnered significant attention, particularly Physics-Informed Neural Networks (PINNs). However, PINNs are typically limited to solving specific problems, and any changes in problem conditions necessitate retraining. Therefore, we explore the generalization capability of transfer learning in the strong and energy form of PINNs across different boundary conditions, materials, and geometries. The transfer learning methods we employ include full finetuning, lightweight finetuning, and Low-Rank Adaptation (LoRA). The results demonstrate that full finetuning and LoRA can significantly improve convergence speed while providing a slight enhancement in accuracy.