用迁移学习让PINN更快适应新边界和材料条件。
Transfer Learning in Physics-Informed Neural Networks: Full Fine-Tuning, Lightweight Fine-Tuning, and Low-Rank Adaptation
- 对比全量微调、轻量微调和低秩适配三种方法
- 全量微调与LoRA显著加快收敛速度，精度略升
- 适合需要快速迁移至新物理问题的研究者
基于PDE的AI已受到广泛关注，尤其是物理信息神经网络（PINNs）。然而，传统PINNs通常仅适用于特定问题，一旦边界条件、材料或几何结构变化，便需重新训练。为此，我们研究了在强形式与能量形式下，针对不同边界条件、材料和几何结构的迁移学习泛化能力。采用的方法包括全量微调、轻量级微调以及低秩适配（LoRA）。实验结果表明，全量微调与LoRA能显著提升收敛速度，同时带来轻微的精度改善。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。