Adaptive transfer learning for PINN | |
Liu Y(刘洋); Liu W(刘文); Yan XS; Guo SQ(郭帅旗); Zhang CA(张陈安) | |
刊名 | Journal of Computational Physics |
2023-10-01 | |
卷号 | 490页码:1 - 29 |
DOI | 10.1016/j.jcp.2023.112291 |
英文摘要 | Physics-informed neural networks (PINNs) have shown great potential in solving computational physics problems with sparse, noisy, unstructured, and multi-fidelity data. However, the training of PINN remains a challenge, and PINN is not robust to deal with some complex problems, such as the sharp local gradient in broad computational domains, etc. Transfer learning techniques can provide fast and accurate training for PINN through intelligent initialization, but the previous researches are much less effective when dealing with transfer learning cases with a large range of parameter variation, which also suffers from the same drawbacks. This manuscript develops the concept of the minimum energy path for PINN and proposes an adaptive transfer learning for PINN (AtPINN). The Partial Differential Equations (PDEs) parameters are initialized by the source parameters and updated adaptively to the target parameters during the training process, which can guide the optimization of PINN from the source to the target task. This process is essentially performed along a designed low-loss path, which is no barrier in the energy landscape of neural networks. Consequently, the stability of the training process is guaranteed. AtPINN is utilized to achieve transfer learning cases with a large range of parameter variation for solving five complex problems. The results demonstrate that AtPINN has promising potential for extending the application of PINN. Besides, three transfer learning cases with different ranges of parameter variation are analyzed through visualization. Furthermore, results also show that the idea of adaptive transfer learning can be a particular optimization strategy to directly solve problems without intelligent initialization. |
分类号 | 一类/力学重要期刊 |
语种 | 英语 |
内容类型 | 期刊论文 |
源URL | [http://dspace.imech.ac.cn/handle/311007/92516] |
专题 | 力学研究所_高温气体动力学国家重点实验室 |
通讯作者 | Liu W(刘文) |
作者单位 | State Key Laboratory of High Temperature Gas Dynamics, Institute of Mechanics, Chinese Academy of Sciences, Beijing 100190, China |
推荐引用方式 GB/T 7714 | Liu Y,Liu W,Yan XS,et al. Adaptive transfer learning for PINN[J]. Journal of Computational Physics,2023,490:1 - 29. |
APA | Liu Y,Liu W,Yan XS,Guo SQ,&Zhang CA.(2023).Adaptive transfer learning for PINN.Journal of Computational Physics,490,1 - 29. |
MLA | Liu Y,et al."Adaptive transfer learning for PINN".Journal of Computational Physics 490(2023):1 - 29. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论