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

arXiv:2211.00713v3 Announce Type: replace
Abstract: 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 …

abstract applications architecture arxiv computational cs.ce cs.lg data deep learning deep learning techniques edge faster fidelity graph mesh network neural network practical predictions prove simulations type