TensorFlow implementation of Graphical Attention Recurrent Neural Networks based on work by Cirstea et al., 2019.
-
Updated
Jan 2, 2020 - Python
TensorFlow implementation of Graphical Attention Recurrent Neural Networks based on work by Cirstea et al., 2019.
From Simone Scala's Master Thesis in Applied Mathematics: applications in Graph Convolutional Neural Networks of the discretized differential p-Laplacian operator as a convolution filter. Numerical experiments using different values of p treating it as an hyperparameter in a grid search. On small datasets. Code not optimized.
Add a description, image, and links to the diffusion-graph-convolution topic page so that developers can more easily learn about it.
To associate your repository with the diffusion-graph-convolution topic, visit your repo's landing page and select "manage topics."