@inproceedings{Tran-2018-filter,
title={On filter size in graph convolutional networks},
author={Tran, Dinh V and Navarin, Nicol{\`o} and Sperduti, Alessandro},
booktitle={2018 IEEE Symposium Series on Computational Intelligence (SSCI)},
pages={1534--1541},
year={2018},
organization={IEEE},
abstract={
Recently, many researchers have been focusing on the definition of neural networks for graphs. The basic component for many of these approaches remains the graph convolution idea proposed almost a decade ago. In this paper, we extend this basic component, following an intuition derived from the well-known convolutional filters over multi-dimensional tensors. In particular, we derive a simple, efficient and effective way to introduce a hyper-parameter on graph convolutions that influences the filter size, i.e., its receptive field over the considered graph. We show with experimental results on real-world graph datasets that the proposed graph convolutional filter improves the predictive performance of Deep Graph Convolutional Networks.
},
  user =	 {miladim}
}