arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.10458cs.LG
收藏

融合框架的算子学习迁移

Transfer Operator Learning with Fusion Frame

The University of Utah(犹他大学)

Haoyang Jiang, Yongzhi Qu

AI总结:

本文提出融合框架与POD-DeepONet结合的架构,增强算子学习模型在偏微分方程求解中的迁移学习能力,实验表明在多种PDE上性能优越。

摘要:

将从一个领域学到的知识应用于解决另一个相关但不同领域的问题,这一挑战被称为迁移学习,在求解偏微分方程(PDEs)的算子学习模型中至关重要。现有的这些模型往往难以在不同任务和数据集之间进行泛化,限制了它们在多样化的科学和工程学科中的适用性。本工作提出了一种新颖的框架,通过将融合框架理论与基于本征正交分解(POD)增强的深度算子网络(DeepONet)相结合,来增强算子学习模型求解偏微分方程(PDEs)的迁移学习能力。我们引入了一种创新的架构,将融合框架与POD-DeepONet相结合,在我们的实验分析中展示了在多种偏微分方程上的优越性能。我们的框架解决了算子学习模型中迁移学习的关键挑战,为在广泛的科学和工程应用中提供适应性强的、高效的解决方案铺平了道路。

英文摘要:

The challenge of applying learned knowledge from one domain to solve problems in another related but distinct domain, known as transfer learning, is fundamental in operator learning models that solve Partial Differential Equations (PDEs). These current models often struggle with generalization across different tasks and datasets, limiting their applicability in diverse scientific and engineering disciplines. This work presents a novel framework that enhances the transfer learning capabilities of operator learning models for solving Partial Differential Equations (PDEs) through the integration of fusion frame theory with the Proper Orthogonal Decomposition (POD)-enhanced Deep Operator Network (DeepONet). We introduce an innovative architecture that combines fusion frames with POD-DeepONet, demonstrating superior performance across various PDEs in our experimental analysis. Our framework addresses the critical challenge of transfer learning in operator learning models, paving the way for adaptable and efficient solutions across a wide range of scientific and engineering applications.

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。

↑