arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.05957cs.LG
收藏

通过在解空间中施加微分算子作用加速偏微分方程数据生成

Accelerating PDE Data Generation via Differential Operator Action in Solution Space

University of Science and Technology of China(中国科学技术大学)

Huanshuo Dong, Hong Wang, Haoyang Liu, Jian Luo, Jie Wang

AI总结:

本文提出DiffOAS算法,通过在解空间中对少量基础PDE解施加微分算子作用来高效生成高精度训练数据,将大规模数据集生成加速300倍,且仅用5%生成时间训练的神经算子即可达到与现有方法相当的性能。

摘要:

近年来,以神经算子(Neural Operator, NO)为代表的数据驱动方法在缩短偏微分方程(Partial Differential Equations, PDEs)求解时间方面展现出显著效果。然而,这些方法面临的一个主要挑战是需要大量高精度训练数据,而数据生成过程需要高昂的计算成本。为应对这一挑战,我们提出了一种新颖的PDE数据集生成算法,即解空间中的微分算子作用(Differential Operator Action in Solution space, DiffOAS),该算法在加速数据生成过程的同时提升生成数据的精度。具体而言,DiffOAS首先获取少量基础PDE解,然后将其组合以得到新解。它在这些解上施加微分算子,这一过程我们称之为“算子作用”,从而高效生成精确的PDE数据点。理论分析表明,DiffOAS方法的时间复杂度比现有生成方法低一个数量级。实验结果显示,DiffOAS将包含10,000个实例的大规模数据集生成过程加速了300倍。即使仅使用5%的生成时间,在DiffOAS生成的数据上训练的NO也表现出与使用现有生成方法训练时相当的性能,这凸显了DiffOAS的高效性。

英文摘要:

Recent advancements in data-driven approaches, such as Neural Operator (NO), have demonstrated their effectiveness in reducing the solving time of Partial Differential Equations (PDEs). However, one major challenge faced by these approaches is the requirement for a large amount of high-precision training data, which needs significant computational costs during the generation process. To address this challenge, we propose a novel PDE dataset generation algorithm, namely Differential Operator Action in Solution space (DiffOAS), which speeds up the data generation process and enhances the precision of the generated data simultaneously. Specifically, DiffOAS obtains a few basic PDE solutions and then combines them to get solutions. It applies differential operators on these solutions, a process we call 'operator action', to efficiently generate precise PDE data points. Theoretical analysis shows that the time complexity of DiffOAS method is one order lower than the existing generation method. Experimental results show that DiffOAS accelerates the generation of large-scale datasets with 10,000 instances by 300 times. Even with just 5% of the generation time, NO trained on the data generated by DiffOAS exhibits comparable performance to that using the existing generation method, which highlights the efficiency of DiffOAS.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑