Learning Convolutional Neural Networks for Graphs
Machine Learning
2016-06-09 v4 Artificial Intelligence
Machine Learning
Abstract
Numerous important problems can be framed as learning from graph data. We propose a framework for learning convolutional neural networks for arbitrary graphs. These graphs may be undirected, directed, and with both discrete and continuous node and edge attributes. Analogous to image-based convolutional networks that operate on locally connected regions of the input, we present a general approach to extracting locally connected regions from graphs. Using established benchmark data sets, we demonstrate that the learned feature representations are competitive with state of the art graph kernels and that their computation is highly efficient.
Cite
@article{arxiv.1605.05273,
title = {Learning Convolutional Neural Networks for Graphs},
author = {Mathias Niepert and Mohamed Ahmed and Konstantin Kutzkov},
journal= {arXiv preprint arXiv:1605.05273},
year = {2016}
}
Comments
To be presented at ICML 2016