Dimension reduced surrogate construction for parametric PDE maps

GCA-ROM is a library which implements graph convolutional autoencoder architecture as a nonlinear model order reduction strategy.

Derivative-Informed Neural Operator: An Efficient Framework for High-Dimensional Parametric Derivative Learning

Graph Feedforward Networks: a resolution-invariant generalisation of feedforward networks for graphical data, applied to model order reduction

Deep Adaptive Sampling for Surrogate Modeling Without Labeled Data

adaptive Stochastic Galerkin finite element methods for parametric PDEs