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 2311.04293cs.LG
收藏

李点对称性与物理信息网络

Lie Point Symmetry and Physics Informed Networks

School of Computer Science, McGill University(麦吉尔大学计算机科学学院);Mila - Quebec Artificial Intelligence Institute(米拉-魁北克人工智能研究所);Université de Montréal(蒙特利尔大学);Ciela Institute(Ciela研究所);Trottier Space Institute(特罗蒂尔空间研究所);CCA, Flatiron Institute(弗拉蒂隆研究所计算天体物理中心);Perimeter Institute(圆周理论物理研究所);Microsoft Research AI4Science(微软研究院AI4Science);University of Amsterdam(阿姆斯特丹大学)

Tara Akhound-Sadegh, Laurence Perreault-Levasseur, Johannes Brandstetter, Max Welling, Siamak Ravanbakhsh

AI总结:

针对偏微分方程神经求解器中对称性整合研究不足的问题,该研究提出在物理信息神经网络中加入李点对称性损失函数,利用其归纳偏置大幅提升了模型的样本效率。

摘要:

对称性已通过从数据增强到等变架构的不同机制被用于提升神经网络的泛化能力。然而,尽管其具备潜力,将其整合到偏微分方程(PDE)神经求解器中的研究仍很大程度上未被探索。我们探索了将PDE对称性(即李点对称性)整合到一类主流神经求解器——物理信息神经网络(PINNs,Physics-Informed Neural Networks)中的方法。我们提出了一种损失函数,以PINN模型通过损失函数强制满足底层PDE的相同方式,向网络传递李点对称性信息。直观来看,我们的对称性损失确保李群的无穷小生成元保持PDE解不变。实际上,这意味着一旦网络学习到一个解,它也能学习到由李点对称性生成的邻近解。实证评估表明,由PDE的李点对称性引入的归纳偏置极大提升了PINNs的样本效率。

英文摘要:

Symmetries have been leveraged to improve the generalization of neural networks through different mechanisms from data augmentation to equivariant architectures. However, despite their potential, their integration into neural solvers for partial differential equations (PDEs) remains largely unexplored. We explore the integration of PDE symmetries, known as Lie point symmetries, in a major family of neural solvers known as physics-informed neural networks (PINNs). We propose a loss function that informs the network about Lie point symmetries in the same way that PINN models try to enforce the underlying PDE through a loss function. Intuitively, our symmetry loss ensures that the infinitesimal generators of the Lie group conserve the PDE solutions. Effectively, this means that once the network learns a solution, it also learns the neighbouring solutions generated by Lie point symmetries. Empirical evaluations indicate that the inductive bias introduced by the Lie point symmetries of the PDEs greatly boosts the sample efficiency of PINNs.

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。

↑