A Survey on Deep Graph Generation: Methods and Applications
Abstract
Graphs are ubiquitous in encoding relational information of real-world objects in many domains. Graph generation, whose purpose is to generate new graphs from a distribution similar to the observed graphs, has received increasing attention thanks to the recent advances of deep learning models. In this paper, we conduct a comprehensive review on the existing literature of deep graph generation from a variety of emerging methods to its wide application areas. Specifically, we first formulate the problem of deep graph generation and discuss its difference with several related graph learning tasks. Secondly, we divide the state-of-the-art methods into three categories based on model architectures and summarize their generation strategies. Thirdly, we introduce three key application areas of deep graph generation. Lastly, we highlight challenges and opportunities in the future study of deep graph generation. We hope that our survey will be useful for researchers and practitioners who are interested in this exciting and rapidly-developing field.
Cite
@article{arxiv.2203.06714,
title = {A Survey on Deep Graph Generation: Methods and Applications},
author = {Yanqiao Zhu and Yuanqi Du and Yinkai Wang and Yichen Xu and Jieyu Zhang and Qiang Liu and Shu Wu},
journal= {arXiv preprint arXiv:2203.06714},
year = {2022}
}
Comments
Accepted to the First Learning on Graphs Conference (LoG 2022)