Deep Graph Generators: A Survey

IEEE Access

Faezeh Faez¹  Mahdieh Soleymani Baghshah¹  Hamid R. Rabiee¹  Yassaman Ommi² 

[1] Department of Computer Engineering, Sharif University of Technology, Tehran, Iran;Department of Mathematics and Computer Science, Amirkabir University of Technology, Tehran, Iran;

关键词: Generative models;    deep learning;    graph data;    deep graph generators;    molecular graph generation;   

DOI  :  10.1109/ACCESS.2021.3098417

来源: DOAJ

【 摘 要 】

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, reinforcement learning-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 review current trends and suggest future research directions based on the existing challenges.

【 授权许可】

Unknown