Deep Graph Generators: A Survey

• DOI: 10.48550/arxiv.2012.15544
• Publication Date: 2020-01-01
• Authors: Faezeh Faez; Yassaman Ommi; Mahdieh Soleymani...; Hamid R. Rabiee
• Keywords: Autoencoder

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