Saved in:
Bibliographic Details
Main Authors: Gao, Yihang, Cheung, Ka Chun, Ng, Michael K.
Format: Preprint
Published: 2022
Subjects:
Online Access:https://arxiv.org/abs/2211.08760
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916159087968256
author Gao, Yihang
Cheung, Ka Chun
Ng, Michael K.
author_facet Gao, Yihang
Cheung, Ka Chun
Ng, Michael K.
contents Physics-informed neural networks (PINNs) have attracted significant attention for solving partial differential equations (PDEs) in recent years because they alleviate the curse of dimensionality that appears in traditional methods. However, the most disadvantage of PINNs is that one neural network corresponds to one PDE. In practice, we usually need to solve a class of PDEs, not just one. With the explosive growth of deep learning, many useful techniques in general deep learning tasks are also suitable for PINNs. Transfer learning methods may reduce the cost for PINNs in solving a class of PDEs. In this paper, we proposed a transfer learning method of PINNs via keeping singular vectors and optimizing singular values (namely SVD-PINNs). Numerical experiments on high dimensional PDEs (10-d linear parabolic equations and 10-d Allen-Cahn equations) show that SVD-PINNs work for solving a class of PDEs with different but close right-hand-side functions.
format Preprint
id arxiv_https___arxiv_org_abs_2211_08760
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle SVD-PINNs: Transfer Learning of Physics-Informed Neural Networks via Singular Value Decomposition
Gao, Yihang
Cheung, Ka Chun
Ng, Michael K.
Machine Learning
Numerical Analysis
Physics-informed neural networks (PINNs) have attracted significant attention for solving partial differential equations (PDEs) in recent years because they alleviate the curse of dimensionality that appears in traditional methods. However, the most disadvantage of PINNs is that one neural network corresponds to one PDE. In practice, we usually need to solve a class of PDEs, not just one. With the explosive growth of deep learning, many useful techniques in general deep learning tasks are also suitable for PINNs. Transfer learning methods may reduce the cost for PINNs in solving a class of PDEs. In this paper, we proposed a transfer learning method of PINNs via keeping singular vectors and optimizing singular values (namely SVD-PINNs). Numerical experiments on high dimensional PDEs (10-d linear parabolic equations and 10-d Allen-Cahn equations) show that SVD-PINNs work for solving a class of PDEs with different but close right-hand-side functions.
title SVD-PINNs: Transfer Learning of Physics-Informed Neural Networks via Singular Value Decomposition
topic Machine Learning
Numerical Analysis
url https://arxiv.org/abs/2211.08760