Deep Learning on Graphs: A Survey

TL;DR

This survey reviews recent deep learning techniques applied to graph data, categorizing methods by architecture and training strategies, and discusses their applications and future research directions.

Contribution

It provides a comprehensive, systematic overview of various deep learning methods on graphs, including their development, differences, and applications.

Findings

Classified methods into five categories: RNNs, CNNs, autoencoders, reinforcement learning, and adversarial methods.

Analyzed differences and compositions of various graph deep learning techniques.

Outlined potential future research directions in graph deep learning.

Abstract

Deep learning has been shown to be 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, substantial research efforts have been devoted to applying deep learning methods to graphs, resulting in beneficial advances in graph analysis techniques. In this survey, we comprehensively review the different types of deep learning methods on graphs. We divide the existing methods into five categories based on their model architectures and training strategies: 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 by following their development history. We also analyze the differences and compositions of different methods. Finally, we briefly outline the applications in which they have been used and discuss potential future research directions.