Megan: A generative adversarial network for multi-view network embedding

Yiwei Sun, Suhang Wang, Tsung Yu Hsieh, Xianfeng Tang, Vasant Honavar

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Data from many real-world applications can be naturally represented by multi-view networks where the different views encode different types of relationships (e.g., friendship, shared interests in music, etc.) between real-world individuals or entities. There is an urgent need for methods to obtain low-dimensional, information preserving and typically nonlinear embeddings of such multi-view networks. However, most of the work on multi-view learning focuses on data that lack a network structure, and most of the work on network embeddings has focused primarily on single-view networks. Against this background, we consider the multi-view network representation learning problem, i.e., the problem of constructing low-dimensional information preserving embeddings of multi-view networks. Specifically, we investigate a novel Generative Adversarial Network (GAN) framework for Multi-View Network Embedding, namely MEGAN, aimed at preserving the information from the individual network views, while accounting for connectivity across (and hence complementarity of and correlations between) different views. The results of our experiments on two real-world multi-view data sets show that the embeddings obtained using MEGAN outperform the state-of-the-art methods on node classification, link prediction and visualization tasks.

Original languageEnglish (US)
Title of host publicationProceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019
EditorsSarit Kraus
PublisherInternational Joint Conferences on Artificial Intelligence
Pages3527-3533
Number of pages7
ISBN (Electronic)9780999241141
StatePublished - Jan 1 2019
Event28th International Joint Conference on Artificial Intelligence, IJCAI 2019 - Macao, China
Duration: Aug 10 2019Aug 16 2019

Publication series

NameIJCAI International Joint Conference on Artificial Intelligence
Volume2019-August
ISSN (Print)1045-0823

Conference

Conference28th International Joint Conference on Artificial Intelligence, IJCAI 2019
CountryChina
CityMacao
Period8/10/198/16/19

Fingerprint

Visualization
Experiments

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Cite this

Sun, Y., Wang, S., Hsieh, T. Y., Tang, X., & Honavar, V. (2019). Megan: A generative adversarial network for multi-view network embedding. In S. Kraus (Ed.), Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019 (pp. 3527-3533). (IJCAI International Joint Conference on Artificial Intelligence; Vol. 2019-August). International Joint Conferences on Artificial Intelligence.
Sun, Yiwei ; Wang, Suhang ; Hsieh, Tsung Yu ; Tang, Xianfeng ; Honavar, Vasant. / Megan : A generative adversarial network for multi-view network embedding. Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019. editor / Sarit Kraus. International Joint Conferences on Artificial Intelligence, 2019. pp. 3527-3533 (IJCAI International Joint Conference on Artificial Intelligence).
@inproceedings{15ca99d016214b06b002a5227edc7c7d,
title = "Megan: A generative adversarial network for multi-view network embedding",
abstract = "Data from many real-world applications can be naturally represented by multi-view networks where the different views encode different types of relationships (e.g., friendship, shared interests in music, etc.) between real-world individuals or entities. There is an urgent need for methods to obtain low-dimensional, information preserving and typically nonlinear embeddings of such multi-view networks. However, most of the work on multi-view learning focuses on data that lack a network structure, and most of the work on network embeddings has focused primarily on single-view networks. Against this background, we consider the multi-view network representation learning problem, i.e., the problem of constructing low-dimensional information preserving embeddings of multi-view networks. Specifically, we investigate a novel Generative Adversarial Network (GAN) framework for Multi-View Network Embedding, namely MEGAN, aimed at preserving the information from the individual network views, while accounting for connectivity across (and hence complementarity of and correlations between) different views. The results of our experiments on two real-world multi-view data sets show that the embeddings obtained using MEGAN outperform the state-of-the-art methods on node classification, link prediction and visualization tasks.",
author = "Yiwei Sun and Suhang Wang and Hsieh, {Tsung Yu} and Xianfeng Tang and Vasant Honavar",
year = "2019",
month = "1",
day = "1",
language = "English (US)",
series = "IJCAI International Joint Conference on Artificial Intelligence",
publisher = "International Joint Conferences on Artificial Intelligence",
pages = "3527--3533",
editor = "Sarit Kraus",
booktitle = "Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019",

}

Sun, Y, Wang, S, Hsieh, TY, Tang, X & Honavar, V 2019, Megan: A generative adversarial network for multi-view network embedding. in S Kraus (ed.), Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019. IJCAI International Joint Conference on Artificial Intelligence, vol. 2019-August, International Joint Conferences on Artificial Intelligence, pp. 3527-3533, 28th International Joint Conference on Artificial Intelligence, IJCAI 2019, Macao, China, 8/10/19.

Megan : A generative adversarial network for multi-view network embedding. / Sun, Yiwei; Wang, Suhang; Hsieh, Tsung Yu; Tang, Xianfeng; Honavar, Vasant.

Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019. ed. / Sarit Kraus. International Joint Conferences on Artificial Intelligence, 2019. p. 3527-3533 (IJCAI International Joint Conference on Artificial Intelligence; Vol. 2019-August).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Megan

T2 - A generative adversarial network for multi-view network embedding

AU - Sun, Yiwei

AU - Wang, Suhang

AU - Hsieh, Tsung Yu

AU - Tang, Xianfeng

AU - Honavar, Vasant

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Data from many real-world applications can be naturally represented by multi-view networks where the different views encode different types of relationships (e.g., friendship, shared interests in music, etc.) between real-world individuals or entities. There is an urgent need for methods to obtain low-dimensional, information preserving and typically nonlinear embeddings of such multi-view networks. However, most of the work on multi-view learning focuses on data that lack a network structure, and most of the work on network embeddings has focused primarily on single-view networks. Against this background, we consider the multi-view network representation learning problem, i.e., the problem of constructing low-dimensional information preserving embeddings of multi-view networks. Specifically, we investigate a novel Generative Adversarial Network (GAN) framework for Multi-View Network Embedding, namely MEGAN, aimed at preserving the information from the individual network views, while accounting for connectivity across (and hence complementarity of and correlations between) different views. The results of our experiments on two real-world multi-view data sets show that the embeddings obtained using MEGAN outperform the state-of-the-art methods on node classification, link prediction and visualization tasks.

AB - Data from many real-world applications can be naturally represented by multi-view networks where the different views encode different types of relationships (e.g., friendship, shared interests in music, etc.) between real-world individuals or entities. There is an urgent need for methods to obtain low-dimensional, information preserving and typically nonlinear embeddings of such multi-view networks. However, most of the work on multi-view learning focuses on data that lack a network structure, and most of the work on network embeddings has focused primarily on single-view networks. Against this background, we consider the multi-view network representation learning problem, i.e., the problem of constructing low-dimensional information preserving embeddings of multi-view networks. Specifically, we investigate a novel Generative Adversarial Network (GAN) framework for Multi-View Network Embedding, namely MEGAN, aimed at preserving the information from the individual network views, while accounting for connectivity across (and hence complementarity of and correlations between) different views. The results of our experiments on two real-world multi-view data sets show that the embeddings obtained using MEGAN outperform the state-of-the-art methods on node classification, link prediction and visualization tasks.

UR - http://www.scopus.com/inward/record.url?scp=85074952534&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85074952534&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85074952534

T3 - IJCAI International Joint Conference on Artificial Intelligence

SP - 3527

EP - 3533

BT - Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019

A2 - Kraus, Sarit

PB - International Joint Conferences on Artificial Intelligence

ER -

Sun Y, Wang S, Hsieh TY, Tang X, Honavar V. Megan: A generative adversarial network for multi-view network embedding. In Kraus S, editor, Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019. International Joint Conferences on Artificial Intelligence. 2019. p. 3527-3533. (IJCAI International Joint Conference on Artificial Intelligence).