Discrete network embedding

Xiaobo Shen, Shirui Pan, Weiwei Liu, Yew Soon Ong, Quan Sen Sun

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

Abstract

Network embedding aims to seek low-dimensional vector representations for network nodes, by preserving the network structure. The network embedding is typically represented in continuous vector, which imposes formidable challenges in storage and computation costs, particularly in large-scale applications. To address the issue, this paper proposes a novel discrete network embedding (DNE) for more compact representations. In particular, DNE learns short binary codes to represent each node. The Hamming similarity between two binary embeddings is then employed to well approximate the ground-truth similarity. A novel discrete multi-class classifier is also developed to expedite classification. Moreover, we propose to jointly learn the discrete embedding and classifier within a unified framework to improve the compactness and discrimination of network embedding. Extensive experiments on node classification consistently demonstrate that DNE exhibits lower storage and computational complexity than state-of-the-art network embedding methods, while obtains competitive classification results.

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
Pages3549-3555
Number of pages7
ISBN (Electronic)9780999241127
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

Cite this

Shen, X., Pan, S., Liu, W., Ong, Y. S., & Sun, Q. S. (2018). Discrete network embedding. In J. Lang (Ed.), Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018 (pp. 3549-3555). California USA: International Joint Conferences on Artificial Intelligence.
Shen, Xiaobo ; Pan, Shirui ; Liu, Weiwei ; Ong, Yew Soon ; Sun, Quan Sen. / Discrete network 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. 3549-3555
@inproceedings{16eac54c941747b6a63087c18e5458b8,
title = "Discrete network embedding",
abstract = "Network embedding aims to seek low-dimensional vector representations for network nodes, by preserving the network structure. The network embedding is typically represented in continuous vector, which imposes formidable challenges in storage and computation costs, particularly in large-scale applications. To address the issue, this paper proposes a novel discrete network embedding (DNE) for more compact representations. In particular, DNE learns short binary codes to represent each node. The Hamming similarity between two binary embeddings is then employed to well approximate the ground-truth similarity. A novel discrete multi-class classifier is also developed to expedite classification. Moreover, we propose to jointly learn the discrete embedding and classifier within a unified framework to improve the compactness and discrimination of network embedding. Extensive experiments on node classification consistently demonstrate that DNE exhibits lower storage and computational complexity than state-of-the-art network embedding methods, while obtains competitive classification results.",
author = "Xiaobo Shen and Shirui Pan and Weiwei Liu and Ong, {Yew Soon} and Sun, {Quan Sen}",
year = "2018",
language = "English",
pages = "3549--3555",
editor = "Jerome Lang",
booktitle = "Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018",
publisher = "International Joint Conferences on Artificial Intelligence",

}

Shen, X, Pan, S, Liu, W, Ong, YS & Sun, QS 2018, Discrete network 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. 3549-3555, International Joint Conference on Artificial Intelligence 2018, Stockholm, Sweden, 13/07/18.

Discrete network embedding. / Shen, Xiaobo; Pan, Shirui; Liu, Weiwei; Ong, Yew Soon; Sun, Quan Sen.

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. 3549-3555.

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

TY - GEN

T1 - Discrete network embedding

AU - Shen, Xiaobo

AU - Pan, Shirui

AU - Liu, Weiwei

AU - Ong, Yew Soon

AU - Sun, Quan Sen

PY - 2018

Y1 - 2018

N2 - Network embedding aims to seek low-dimensional vector representations for network nodes, by preserving the network structure. The network embedding is typically represented in continuous vector, which imposes formidable challenges in storage and computation costs, particularly in large-scale applications. To address the issue, this paper proposes a novel discrete network embedding (DNE) for more compact representations. In particular, DNE learns short binary codes to represent each node. The Hamming similarity between two binary embeddings is then employed to well approximate the ground-truth similarity. A novel discrete multi-class classifier is also developed to expedite classification. Moreover, we propose to jointly learn the discrete embedding and classifier within a unified framework to improve the compactness and discrimination of network embedding. Extensive experiments on node classification consistently demonstrate that DNE exhibits lower storage and computational complexity than state-of-the-art network embedding methods, while obtains competitive classification results.

AB - Network embedding aims to seek low-dimensional vector representations for network nodes, by preserving the network structure. The network embedding is typically represented in continuous vector, which imposes formidable challenges in storage and computation costs, particularly in large-scale applications. To address the issue, this paper proposes a novel discrete network embedding (DNE) for more compact representations. In particular, DNE learns short binary codes to represent each node. The Hamming similarity between two binary embeddings is then employed to well approximate the ground-truth similarity. A novel discrete multi-class classifier is also developed to expedite classification. Moreover, we propose to jointly learn the discrete embedding and classifier within a unified framework to improve the compactness and discrimination of network embedding. Extensive experiments on node classification consistently demonstrate that DNE exhibits lower storage and computational complexity than state-of-the-art network embedding methods, while obtains competitive classification results.

UR - http://www.scopus.com/inward/record.url?scp=85055684784&partnerID=8YFLogxK

M3 - Conference Paper

SP - 3549

EP - 3555

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 -

Shen X, Pan S, Liu W, Ong YS, Sun QS. Discrete network 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. 3549-3555