Learning Deep Graph Representations via Convolutional Neural Networks
This work addresses graph classification tasks in scenarios with graph-structured data, representing an incremental improvement over existing methods.
The paper tackled the problem of quantifying graph similarities for classification by addressing the high-dimensional feature space and inability to capture high-order interactions in existing graph kernels, resulting in a framework called DeepMap that achieved state-of-the-art performance on various benchmarks.
Graph-structured data arise in many scenarios. A fundamental problem is to quantify the similarities of graphs for tasks such as classification. R-convolution graph kernels are positive-semidefinite functions that decompose graphs into substructures and compare them. One problem in the effective implementation of this idea is that the substructures are not independent, which leads to high-dimensional feature space. In addition, graph kernels cannot capture the high-order complex interactions between vertices. To mitigate these two problems, we propose a framework called DeepMap to learn deep representations for graph feature maps. The learned deep representation for a graph is a dense and low-dimensional vector that captures complex high-order interactions in a vertex neighborhood. DeepMap extends Convolutional Neural Networks (CNNs) to arbitrary graphs by generating aligned vertex sequences and building the receptive field for each vertex. We empirically validate DeepMap on various graph classification benchmarks and demonstrate that it achieves state-of-the-art performance.