Learning Convolutional Neural Networks for Graphs
This work addresses the challenge of applying convolutional neural networks to graph-structured data, which is incremental as it adapts existing image-based methods to graphs.
The authors tackled the problem of learning from arbitrary graph data by proposing a convolutional neural network framework that operates on locally connected regions of graphs, demonstrating competitive performance with state-of-the-art graph kernels and high computational efficiency on benchmark datasets.
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.