Enregistré dans:
Détails bibliographiques
Auteurs principaux: Liang, Aoming, Mu, Zhaoyang, Lin, Pengxiao, Wang, Cong, Ge, Mingming, Shao, Ling, Fan, Dixia, Tang, Hao
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2410.11617
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866929543795703808
author Liang, Aoming
Mu, Zhaoyang
Lin, Pengxiao
Wang, Cong
Ge, Mingming
Shao, Ling
Fan, Dixia
Tang, Hao
author_facet Liang, Aoming
Mu, Zhaoyang
Lin, Pengxiao
Wang, Cong
Ge, Mingming
Shao, Ling
Fan, Dixia
Tang, Hao
contents Learning the evolutionary dynamics of Partial Differential Equations (PDEs) is critical in understanding dynamic systems, yet current methods insufficiently learn their representations. This is largely due to the multi-scale nature of the solution, where certain regions exhibit rapid oscillations while others evolve more slowly. This paper introduces a framework of multi-scale and multi-expert (M$^2$M) neural operators designed to simulate and learn PDEs efficiently. We employ a divide-and-conquer strategy to train a multi-expert gated network for the dynamic router policy. Our method incorporates a controllable prior gating mechanism that determines the selection rights of experts, enhancing the model's efficiency. To optimize the learning process, we have implemented a PI (Proportional, Integral) control strategy to adjust the allocation rules precisely. This universal controllable approach allows the model to achieve greater accuracy. We test our approach on benchmark 2D Navier-Stokes equations and provide a custom multi-scale dataset. M$^2$M can achieve higher simulation accuracy and offer improved interpretability compared to baseline methods.
format Preprint
id arxiv_https___arxiv_org_abs_2410_11617
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle M$^{2}$M: Learning controllable Multi of experts and multi-scale operators are the Partial Differential Equations need
Liang, Aoming
Mu, Zhaoyang
Lin, Pengxiao
Wang, Cong
Ge, Mingming
Shao, Ling
Fan, Dixia
Tang, Hao
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Learning the evolutionary dynamics of Partial Differential Equations (PDEs) is critical in understanding dynamic systems, yet current methods insufficiently learn their representations. This is largely due to the multi-scale nature of the solution, where certain regions exhibit rapid oscillations while others evolve more slowly. This paper introduces a framework of multi-scale and multi-expert (M$^2$M) neural operators designed to simulate and learn PDEs efficiently. We employ a divide-and-conquer strategy to train a multi-expert gated network for the dynamic router policy. Our method incorporates a controllable prior gating mechanism that determines the selection rights of experts, enhancing the model's efficiency. To optimize the learning process, we have implemented a PI (Proportional, Integral) control strategy to adjust the allocation rules precisely. This universal controllable approach allows the model to achieve greater accuracy. We test our approach on benchmark 2D Navier-Stokes equations and provide a custom multi-scale dataset. M$^2$M can achieve higher simulation accuracy and offer improved interpretability compared to baseline methods.
title M$^{2}$M: Learning controllable Multi of experts and multi-scale operators are the Partial Differential Equations need
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.11617