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 2211.00713cs.LGcs.CE
收藏

MAgNET:一种用于基于网格仿真的图 U-Net 架构

MAgNET: A Graph U-Net Architecture for Mesh-Based Simulations

University of Luxembourg(卢森堡大学);Institute of Fundamental Technological Research, Polish Academy of Sciences(波兰科学院基础技术研究所)

Saurabh Deshpande, Stéphane P. A. Bordas, Jakub Lengiewicz

AI总结:

本文提出图 U-Net 架构 MAgNET,通过多通道聚合层与图池化/反池化层将卷积神经网络扩展到任意图结构数据,并验证了其在固体力学非线性有限元仿真代理建模中的预测能力。

摘要:

在许多前沿应用中,高保真计算模型被证明对于实际使用而言过于缓慢,因此被速度更快的代理模型所取代。近年来,深度学习技术越来越多地被用于加速此类预测。为了能够在大维度且复杂的数据上进行学习,人们开发了特定的神经网络架构,包括卷积神经网络和图神经网络。在这项工作中,我们提出了一种新颖的编码器-解码器几何深度学习框架,称为 MAgNET,它扩展了众所周知的卷积神经网络以适应任意图结构数据。MAgNET 由创新的多通道聚合(MAg)层和图池化/反池化层组成,形成了一种类似于卷积 U-Net 的图 U-Net 架构。我们展示了 MAgNET 在固体力学中非线性有限元仿真的代理建模中的预测能力。

英文摘要:

In many cutting-edge applications, high-fidelity computational models prove to be too slow for practical use and are therefore replaced by much faster surrogate models. Recently, deep learning techniques have increasingly been utilized to accelerate such predictions. To enable learning on large-dimensional and complex data, specific neural network architectures have been developed, including convolutional and graph neural networks. In this work, we present a novel encoder-decoder geometric deep learning framework called MAgNET, which extends the well-known convolutional neural networks to accommodate arbitrary graph-structured data. MAgNET consists of innovative Multichannel Aggregation (MAg) layers and graph pooling/unpooling layers, forming a graph U-Net architecture that is analogous to convolutional U-Nets. We demonstrate the predictive capabilities of MAgNET in surrogate modeling for non-linear finite element simulations in the mechanics of solids.

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。

↑