Toward a Better Understanding of Fourier Neural Operators from a Spectral Perspective

• URL: http://arxiv.org/abs/2404.07200v2
• Date: Wed, 09 Oct 2024 04:43:57 GMT
• Title: Toward a Better Understanding of Fourier Neural Operators from a Spectral Perspective
• Authors: Shaoxiang Qin, Fuyuan Lyu, Wenhui Peng, Dingyang Geng, Ju Wang, Xing Tang, Sylvie Leroyer, Naiping Gao, Xue Liu, Liangzhu Leon Wang,
• Abstract summary: SpecB-FNO achieves better prediction accuracy on diverse PDE applications, with an average improvement of 50%. This paper offers empirical insights into FNO's difficulty with large kernels through spectral analysis.
• Score: 4.315136713224842
• License:
• Abstract: In solving partial differential equations (PDEs), Fourier Neural Operators (FNOs) have exhibited notable effectiveness. However, FNO is observed to be ineffective with large Fourier kernels that parameterize more frequencies. Current solutions rely on setting small kernels, restricting FNO's ability to capture complex PDE data in real-world applications. This paper offers empirical insights into FNO's difficulty with large kernels through spectral analysis: FNO exhibits a unique Fourier parameterization bias, excelling at learning dominant frequencies in target data while struggling with non-dominant frequencies. To mitigate such a bias, we propose SpecB-FNO to enhance the capture of non-dominant frequencies by adopting additional residual modules to learn from the previous ones' prediction residuals iteratively. By effectively utilizing large Fourier kernels, SpecB-FNO achieves better prediction accuracy on diverse PDE applications, with an average improvement of 50%.

Related papers

Err

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.