Deep Graph Generators: A Survey

TL;DR

This survey reviews recent deep learning methods for graph generation, categorizing approaches, discussing datasets and metrics, and highlighting challenges and future directions in the field.

Contribution

It provides a comprehensive classification and analysis of deep graph generation techniques, including source code and evaluation tools, which was lacking in prior literature.

Findings

Classified graph generation methods into five categories

Compiled publicly available datasets and source codes

Discussed key challenges and future research directions

Abstract

Deep generative models have achieved great success in areas such as image, speech, and natural language processing in the past few years. Thanks to the advances in graph-based deep learning, and in particular graph representation learning, deep graph generation methods have recently emerged with new applications ranging from discovering novel molecular structures to modeling social networks. This paper conducts a comprehensive survey on deep learning-based graph generation approaches and classifies them into five broad categories, namely, autoregressive, autoencoder-based, RL-based, adversarial, and flow-based graph generators, providing the readers a detailed description of the methods in each class. We also present publicly available source codes, commonly used datasets, and the most widely utilized evaluation metrics. Finally, we highlight the existing challenges and discuss future research directions.