A Survey on Deep Graph Generation: Methods and Applications

Yanqiao Zhu, Yuanqi Du, Yinkai Wang, Yichen Xu, Jieyu Zhang, Qiang Liu, Shu Wu
Proceedings of the First Learning on Graphs Conference, PMLR 198:47:1-47:21, 2022.

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 this Paper

BibTeX
@InProceedings{pmlr-v198-zhu22a, title = {A Survey on Deep Graph Generation: Methods and Applications}, author = {Zhu, Yanqiao and Du, Yuanqi and Wang, Yinkai and Xu, Yichen and Zhang, Jieyu and Liu, Qiang and Wu, Shu}, booktitle = {Proceedings of the First Learning on Graphs Conference}, pages = {47:1--47:21}, year = {2022}, editor = {Rieck, Bastian and Pascanu, Razvan}, volume = {198}, series = {Proceedings of Machine Learning Research}, month = {09--12 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v198/zhu22a/zhu22a.pdf}, url = {https://proceedings.mlr.press/v198/zhu22a.html}, 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.} }
Endnote
%0 Conference Paper %T A Survey on Deep Graph Generation: Methods and Applications %A Yanqiao Zhu %A Yuanqi Du %A Yinkai Wang %A Yichen Xu %A Jieyu Zhang %A Qiang Liu %A Shu Wu %B Proceedings of the First Learning on Graphs Conference %C Proceedings of Machine Learning Research %D 2022 %E Bastian Rieck %E Razvan Pascanu %F pmlr-v198-zhu22a %I PMLR %P 47:1--47:21 %U https://proceedings.mlr.press/v198/zhu22a.html %V 198 %X 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.
APA
Zhu, Y., Du, Y., Wang, Y., Xu, Y., Zhang, J., Liu, Q. & Wu, S.. (2022). A Survey on Deep Graph Generation: Methods and Applications. Proceedings of the First Learning on Graphs Conference, in Proceedings of Machine Learning Research 198:47:1-47:21 Available from https://proceedings.mlr.press/v198/zhu22a.html.

Related Material