ARTICLE | doi:10.20944/preprints202302.0026.v1
Subject: Computer Science And Mathematics, Computer Vision And Graphics Keywords: Graph Neural Network; Variational Autoencoder; Pooling; Nearest Neighbours
Online: 2 February 2023 (03:36:17 CET)
We present a Deep Learning generative model specialized to work with graphs with a regular geometry. It is build on a Variational Autoencoder framework and employs Graph convolutional layers in both encoding and decoding phases. We also introduce a pooling technique (ReNN-Pool), used in the encoder, that allows to downsample graph nodes in a spatially uniform and highly interpretable way. In the decoder, a symmetrical un-pooling technique is used to retrieve the original dimensionality of graphs. Performance of the model are tested on the standard Sprite benchmark dataset, a set of 2D images of video game characters, adequately transforming images data into graphs, and on the more realistic use-case of a dataset of cylindrical-shaped graph data that describe the distributions of the energy deposited by a particle beam in a medium.