Classifying Graphs as Images with Convolutional Neural Networks
share
The task of graph classification is currently dominated by graph kernels, which, while powerful, scale poorly to large graphs and datasets. Convolutional Neural Networks (CNNs) offer a very appealing alternative. However, feeding graphs to CNNs is not trivial. To address this challenge, many sophisticated extensions of CNNs have recently been proposed. In this paper, we show that a classical 2D CNN architecture designed for images can also be used for graph processing in a completely off-the-shelf manner; the only prerequisite being to encode graphs as stacks of two-dimensional histograms of their node embeddings. Despite its simplicity, our method proves very competitive to state-of-the-art graph kernels, and even outperforms them by a wide margin on some datasets.
READ FULL TEXT