Simple Graph Convolutional Networks
Machine Learning
2021-06-11 v1
Abstract
Many neural networks for graphs are based on the graph convolution operator, proposed more than a decade ago. Since then, many alternative definitions have been proposed, that tend to add complexity (and non-linearity) to the model. In this paper, we follow the opposite direction by proposing simple graph convolution operators, that can be implemented in single-layer graph convolutional networks. We show that our convolution operators are more theoretically grounded than many proposals in literature, and exhibit state-of-the-art predictive performance on the considered benchmark datasets.
Cite
@article{arxiv.2106.05809,
title = {Simple Graph Convolutional Networks},
author = {Luca Pasa and Nicolò Navarin and Wolfgang Erb and Alessandro Sperduti},
journal= {arXiv preprint arXiv:2106.05809},
year = {2021}
}