Eprint already available on another site (E-prints, Working papers and Research blog)
MAgNET: A Graph U-Net Architecture for Mesh-Based Simulations
DESHPANDE, Saurabh; BORDAS, Stéphane; LENGIEWICZ, Jakub
2023
 

Files


Full Text
2211.00713.pdf
Author preprint (17.36 MB)
Download

All documents in ORBilu are protected by a user license.

Send to



Details



Abstract :
[en] In many cutting-edge applications, high-fidelity computational models prove too slow to be practical and are thus replaced by much faster surrogate models. Recently, deep learning techniques have become increasingly important in accelerating such predictions. However, they tend to falter when faced with larger and more complex problems. Therefore, this work introduces MAgNET: Multi-channel Aggregation Network, a novel geometric deep learning framework designed to operate on large-dimensional data of arbitrary structure (graph data). MAgNET is built upon the MAg (Multichannel Aggregation) operation, which generalizes the concept of multi-channel local operations in convolutional neural networks to arbitrary non-grid inputs. The MAg layers are interleaved with the proposed novel graph pooling/unpooling operations to form a graph U-Net architecture that is robust and can handle arbitrary complex meshes, efficiently performing supervised learning on large- dimensional graph-structured data. We demonstrate the predictive capabilities of MAgNET for several non-linear finite element simulations and provide open-source datasets and codes to facilitate future research.
Disciplines :
Engineering, computing & technology: Multidisciplinary, general & others
Author, co-author :
DESHPANDE, Saurabh  ;  University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Engineering (DoE)
BORDAS, Stéphane ;  University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Engineering (DoE)
LENGIEWICZ, Jakub ;  University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Engineering (DoE)
Language :
English
Title :
MAgNET: A Graph U-Net Architecture for Mesh-Based Simulations
Publication date :
March 2023
Focus Area :
Computational Sciences
European Projects :
H2020 - 764644 - RAINBOW - Rapid Biomechanics Simulation for Personalized Clinical Design
FnR Project :
FNR14782078 - Quantum-continuum Bridging, 2020 (01/09/2021-31/08/2024) - Stéphane Bordas
Funders :
CE - Commission Européenne
Available on ORBilu :
since 02 May 2023

Statistics


Number of views
88 (13 by Unilu)
Number of downloads
121 (3 by Unilu)

OpenAlex citations
 
13

Bibliography


Similar publications



Contact ORBilu