Transfer Learning in Physics-Informed Neural Networks: Full Fine-Tuning, Lightweight Fine-Tuning, and Low-Rank Adaptation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912216685477888 |
|---|---|
| author | Wang, Yizheng Bai, Jinshuai Eshaghi, Mohammad Sadegh Anitescu, Cosmin Zhuang, Xiaoying Rabczuk, Timon Liu, Yinghua |
| author_facet | Wang, Yizheng Bai, Jinshuai Eshaghi, Mohammad Sadegh Anitescu, Cosmin Zhuang, Xiaoying Rabczuk, Timon Liu, Yinghua |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_00782 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Transfer Learning in Physics-Informed Neural Networks: Full Fine-Tuning, Lightweight Fine-Tuning, and Low-Rank Adaptation Wang, Yizheng Bai, Jinshuai Eshaghi, Mohammad Sadegh Anitescu, Cosmin Zhuang, Xiaoying Rabczuk, Timon Liu, Yinghua Machine Learning 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. |
| title | Transfer Learning in Physics-Informed Neural Networks: Full Fine-Tuning, Lightweight Fine-Tuning, and Low-Rank Adaptation |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2502.00782 |