Adversarially regularized graph autoencoder for graph embedding

Shirui Pan, Ruiqi Hu, Guodong Long, Jing Jiang, Lina Yao, Chengqi Zhang

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

Abstract

Graph embedding is an effective method to represent graph data in a low dimensional space for graph analytics. Most existing embedding algorithms typically focus on preserving the topological structure or minimizing the reconstruction errors of graph data, but they have mostly ignored the data distribution of the latent codes from the graphs, which often results in inferior embedding in real-world graph data. In this paper, we propose a novel adversarial graph embedding framework for graph data. The framework encodes the topological structure and node content in a graph to a compact representation, on which a decoder is trained to reconstruct the graph structure. Furthermore, the latent representation is enforced to match a prior distribution via an adversarial training scheme. To learn a robust embedding, two variants of adversarial approaches, adversarially regularized graph autoencoder (ARGA) and adversarially regularized variational graph autoencoder (ARVGA), are developed. Experimental studies on real-world graphs validate our design and demonstrate that our algorithms outperform baselines by a wide margin in link prediction, graph clustering, and graph visualization tasks.

Original languageEnglish
Title of host publicationProceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018
EditorsJerome Lang
Place of PublicationCalifornia USA
PublisherInternational Joint Conferences on Artificial Intelligence
Pages2609-2615
Number of pages7
ISBN (Electronic)9780999241127
DOIs
Publication statusPublished - 2018
Externally publishedYes
EventInternational Joint Conference on Artificial Intelligence 2018 - Stockholm, Sweden
Duration: 13 Jul 201819 Jul 2018
https://www.ijcai.org/proceedings/2018/

Conference

ConferenceInternational Joint Conference on Artificial Intelligence 2018
Abbreviated titleIJCAI 2018
CountrySweden
CityStockholm
Period13/07/1819/07/18
Internet address

Keywords

  • Data Mining
  • Unsupervised Learning
  • Networks
  • Machine Learning
  • Machine Learning Application

Cite this

Pan, S., Hu, R., Long, G., Jiang, J., Yao, L., & Zhang, C. (2018). Adversarially regularized graph autoencoder for graph embedding. In J. Lang (Ed.), Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018 (pp. 2609-2615). California USA: International Joint Conferences on Artificial Intelligence. https://doi.org/10.24963/ijcai.2018/362
Pan, Shirui ; Hu, Ruiqi ; Long, Guodong ; Jiang, Jing ; Yao, Lina ; Zhang, Chengqi. / Adversarially regularized graph autoencoder for graph embedding. Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018. editor / Jerome Lang. California USA : International Joint Conferences on Artificial Intelligence, 2018. pp. 2609-2615
@inproceedings{972765c0ec4549d2b86f038ee40e3d86,
title = "Adversarially regularized graph autoencoder for graph embedding",
abstract = "Graph embedding is an effective method to represent graph data in a low dimensional space for graph analytics. Most existing embedding algorithms typically focus on preserving the topological structure or minimizing the reconstruction errors of graph data, but they have mostly ignored the data distribution of the latent codes from the graphs, which often results in inferior embedding in real-world graph data. In this paper, we propose a novel adversarial graph embedding framework for graph data. The framework encodes the topological structure and node content in a graph to a compact representation, on which a decoder is trained to reconstruct the graph structure. Furthermore, the latent representation is enforced to match a prior distribution via an adversarial training scheme. To learn a robust embedding, two variants of adversarial approaches, adversarially regularized graph autoencoder (ARGA) and adversarially regularized variational graph autoencoder (ARVGA), are developed. Experimental studies on real-world graphs validate our design and demonstrate that our algorithms outperform baselines by a wide margin in link prediction, graph clustering, and graph visualization tasks.",
keywords = "Data Mining, Unsupervised Learning, Networks, Machine Learning, Machine Learning Application",
author = "Shirui Pan and Ruiqi Hu and Guodong Long and Jing Jiang and Lina Yao and Chengqi Zhang",
year = "2018",
doi = "10.24963/ijcai.2018/362",
language = "English",
pages = "2609--2615",
editor = "Jerome Lang",
booktitle = "Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018",
publisher = "International Joint Conferences on Artificial Intelligence",

}

Pan, S, Hu, R, Long, G, Jiang, J, Yao, L & Zhang, C 2018, Adversarially regularized graph autoencoder for graph embedding. in J Lang (ed.), Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018. International Joint Conferences on Artificial Intelligence, California USA, pp. 2609-2615, International Joint Conference on Artificial Intelligence 2018, Stockholm, Sweden, 13/07/18. https://doi.org/10.24963/ijcai.2018/362

Adversarially regularized graph autoencoder for graph embedding. / Pan, Shirui; Hu, Ruiqi; Long, Guodong; Jiang, Jing; Yao, Lina; Zhang, Chengqi.

Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018. ed. / Jerome Lang. California USA : International Joint Conferences on Artificial Intelligence, 2018. p. 2609-2615.

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

TY - GEN

T1 - Adversarially regularized graph autoencoder for graph embedding

AU - Pan, Shirui

AU - Hu, Ruiqi

AU - Long, Guodong

AU - Jiang, Jing

AU - Yao, Lina

AU - Zhang, Chengqi

PY - 2018

Y1 - 2018

N2 - Graph embedding is an effective method to represent graph data in a low dimensional space for graph analytics. Most existing embedding algorithms typically focus on preserving the topological structure or minimizing the reconstruction errors of graph data, but they have mostly ignored the data distribution of the latent codes from the graphs, which often results in inferior embedding in real-world graph data. In this paper, we propose a novel adversarial graph embedding framework for graph data. The framework encodes the topological structure and node content in a graph to a compact representation, on which a decoder is trained to reconstruct the graph structure. Furthermore, the latent representation is enforced to match a prior distribution via an adversarial training scheme. To learn a robust embedding, two variants of adversarial approaches, adversarially regularized graph autoencoder (ARGA) and adversarially regularized variational graph autoencoder (ARVGA), are developed. Experimental studies on real-world graphs validate our design and demonstrate that our algorithms outperform baselines by a wide margin in link prediction, graph clustering, and graph visualization tasks.

AB - Graph embedding is an effective method to represent graph data in a low dimensional space for graph analytics. Most existing embedding algorithms typically focus on preserving the topological structure or minimizing the reconstruction errors of graph data, but they have mostly ignored the data distribution of the latent codes from the graphs, which often results in inferior embedding in real-world graph data. In this paper, we propose a novel adversarial graph embedding framework for graph data. The framework encodes the topological structure and node content in a graph to a compact representation, on which a decoder is trained to reconstruct the graph structure. Furthermore, the latent representation is enforced to match a prior distribution via an adversarial training scheme. To learn a robust embedding, two variants of adversarial approaches, adversarially regularized graph autoencoder (ARGA) and adversarially regularized variational graph autoencoder (ARVGA), are developed. Experimental studies on real-world graphs validate our design and demonstrate that our algorithms outperform baselines by a wide margin in link prediction, graph clustering, and graph visualization tasks.

KW - Data Mining

KW - Unsupervised Learning

KW - Networks

KW - Machine Learning

KW - Machine Learning Application

UR - http://www.scopus.com/inward/record.url?scp=85055684972&partnerID=8YFLogxK

U2 - 10.24963/ijcai.2018/362

DO - 10.24963/ijcai.2018/362

M3 - Conference Paper

SP - 2609

EP - 2615

BT - Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018

A2 - Lang, Jerome

PB - International Joint Conferences on Artificial Intelligence

CY - California USA

ER -

Pan S, Hu R, Long G, Jiang J, Yao L, Zhang C. Adversarially regularized graph autoencoder for graph embedding. In Lang J, editor, Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018. California USA: International Joint Conferences on Artificial Intelligence. 2018. p. 2609-2615 https://doi.org/10.24963/ijcai.2018/362