Learning Convolutional Neural Networks for Graphs

TLDR

Numerous important problems can be framed as learning from graph data. We propose a framework for learning convolutional neural networks for arbitrary graphs. The framework handles arbitrary graphs—including undirected, directed, and graphs with discrete or continuous node and edge attributes—and extracts locally connected regions analogous to image‑based convolutional networks. 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.

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.