Geometric Neural Operators (GNPs) for Data-Driven Deep Learning of Non-Euclidean Operators

2024/04/16 by Quackenbush, Blaine, Atzberger, Paul J.
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Optimization and Control (math.OC)

paper · doi:10.48550/arxiv.2404.10843

Abstract

We introduce Geometric Neural Operators (GNPs) for accounting for geometric contributions in data-driven deep learning of operators. We show how GNPs can be used (i) to estimate geometric properties, such as the metric and curvatures, (ii) to approximate Partial Differential Equations (PDEs) on manifolds, (iii) learn solution maps for Laplace-Beltrami (LB) operators, and (iv) to solve Bayesian inverse problems for identifying manifold shapes. The methods allow for handling geometries of general shape including point-cloud representations. The developed GNPs provide approaches for incorporating the roles of geometry in data-driven learning of operators.

Related

• Transferable Foundation Models for Geometric Tasks on Point Cloud Representations: Geometric Neural Operators
• Geometric Deep Learning: Going beyond Euclidean data
• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
• Reference Neural Operators: Learning the Smooth Dependence of Solutions of PDEs on Geometric Deformations
• Geometric Laplace Neural Operator