Deep learning has been shown successful in a number of domains, ranging from acoustics, images to natural language processing. However, applying deep learning to the ubiquitous graph data is non-trivial because of the unique characteristics of graphs. Recently, a significant amount of research efforts have been devoted to this area, greatly advancing graph analyzing techniques. In this survey, we comprehensively review different kinds of deep learning methods applied to graphs. We divide existing methods into five categories based on their model architectures: Graph Recurrent Neural Networks, Graph Convolutional Networks, Graph Autoencoders, Graph Reinforcement Learning, and Graph Adversarial Methods. We then provide a comprehensive overview of these methods in a systematic manner mainly following their history of developments. We also analyze the differences and compositionality of different architectures. Finally, we briefly outline their applications and discuss potential future directions.
View on arXiv