Graph Capsule Convolutional Neural Networks
It addresses graph classification, a challenging problem for domains like bioinformatics and social networks, with an incremental improvement over GCNNs.
The paper tackles weaknesses in Graph Convolutional Neural Networks (GCNNs) by introducing a Graph Capsule Network (GCAPS-CNN) for graph classification, showing it significantly outperforms existing state-of-the-art methods and graph kernels on benchmark datasets.
Graph Convolutional Neural Networks (GCNNs) are the most recent exciting advancement in deep learning field and their applications are quickly spreading in multi-cross-domains including bioinformatics, chemoinformatics, social networks, natural language processing and computer vision. In this paper, we expose and tackle some of the basic weaknesses of a GCNN model with a capsule idea presented in \cite{hinton2011transforming} and propose our Graph Capsule Network (GCAPS-CNN) model. In addition, we design our GCAPS-CNN model to solve especially graph classification problem which current GCNN models find challenging. Through extensive experiments, we show that our proposed Graph Capsule Network can significantly outperforms both the existing state-of-art deep learning methods and graph kernels on graph classification benchmark datasets.