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

GCA-ROM requires pytorch, pyg, matplotlib, scipy and h5py. They can be easily installed via pip or conda.

The official distribution is on GitHub, and you can clone the repository using

git clone git@github.com:fpichi/gca-rom.git

1. a graph-based layer to express an unstructured dataset;
2. an encoder module compressing the information through:
   1. spatial convolutional layers based on MoNet [57] to identify patterns between geomet- rically close regions;
   2. skip-connection operation, to keep track of the original information and help the learn- ing procedure;
   3. a pooling operation, to down-sample the data to obtain smaller networks;
3. a bottleneck, connected to the encoder by means of a dense layer, which contains the latent behavior in a vector;
4. a decoder module, recovering the original data by applying the same operations as in the encoder, but in reverse order.

Pichi, F., Moya, B. and Hesthaven, J.S. (2023) ‘A graph convolutional autoencoder approach to model order reduction for parametrized PDEs’. Available at: arXiv.

If you use GCA-ROM for academic research, you are encouraged to cite the paper using:

@misc{PichiGraphConvolutionalAutoencoder2023,
  title = {A Graph Convolutional Autoencoder Approach to Model Order Reduction for Parametrized {{PDEs}}},
  author = {Pichi, Federico and Moya, Beatriz and Hesthaven, Jan S.},
  year = {2023},
  number = {arXiv:2305.08573},
  eprint = {2305.08573},
  primaryclass = {cs, math},
  publisher = {{arXiv}},
  doi = {10.48550/arXiv.2305.08573},
  archiveprefix = {arxiv}
}

• Federico Pichi (federico.pichi@epfl.ch)
• Beatriz Moya García (beatriz.moya@cnrsatcreate.sg)

in collaboration with the MCSS group at EPFL of Prof. Jan S. Hesthaven

Made with contrib.rocks.