Marine

Multi-relational network embeddings with relational proximity and node attributes

Ming Han Feng, Chin Chi Hsu, Cheng-Te Li, Mi Yen Yeh, Shou De Lin

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

Abstract

Network embedding aims at learning an effective vector transformation for entities in a network. We observe that there are two diverse branches of network embedding: for homogeneous graphs and for multi-relational graphs. This paper then proposes MARINE, a unified embedding framework for both homogeneous and multi-relational networks to preserve both the proximity and relation information. We also extend the framework to incorporate existing features of nodes in a graph, which can further be exploited for the ensemble of embedding. Our solution possesses complexity linear to the number of edges, which is suitable for large-scale network applications. Experiments conducted on several real-world network datasets, along with applications in link prediction and multi-label classification, exhibit the superiority of our proposed MARINE.

Original languageEnglish
Title of host publicationThe Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019
PublisherAssociation for Computing Machinery, Inc
Pages470-479
Number of pages10
ISBN (Electronic)9781450366748
DOIs
Publication statusPublished - 2019 May 13
Event2019 World Wide Web Conference, WWW 2019 - San Francisco, United States
Duration: 2019 May 132019 May 17

Publication series

NameThe Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019

Conference

Conference2019 World Wide Web Conference, WWW 2019
CountryUnited States
CitySan Francisco
Period19-05-1319-05-17

Fingerprint

Labels
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Software

Cite this

Feng, M. H., Hsu, C. C., Li, C-T., Yeh, M. Y., & Lin, S. D. (2019). Marine: Multi-relational network embeddings with relational proximity and node attributes. In The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019 (pp. 470-479). (The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019). Association for Computing Machinery, Inc. https://doi.org/10.1145/3308558.3313715
Feng, Ming Han ; Hsu, Chin Chi ; Li, Cheng-Te ; Yeh, Mi Yen ; Lin, Shou De. / Marine : Multi-relational network embeddings with relational proximity and node attributes. The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019. Association for Computing Machinery, Inc, 2019. pp. 470-479 (The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019).
@inproceedings{1c3956c3dd83477ba4615df459a0e0b4,
title = "Marine: Multi-relational network embeddings with relational proximity and node attributes",
abstract = "Network embedding aims at learning an effective vector transformation for entities in a network. We observe that there are two diverse branches of network embedding: for homogeneous graphs and for multi-relational graphs. This paper then proposes MARINE, a unified embedding framework for both homogeneous and multi-relational networks to preserve both the proximity and relation information. We also extend the framework to incorporate existing features of nodes in a graph, which can further be exploited for the ensemble of embedding. Our solution possesses complexity linear to the number of edges, which is suitable for large-scale network applications. Experiments conducted on several real-world network datasets, along with applications in link prediction and multi-label classification, exhibit the superiority of our proposed MARINE.",
author = "Feng, {Ming Han} and Hsu, {Chin Chi} and Cheng-Te Li and Yeh, {Mi Yen} and Lin, {Shou De}",
year = "2019",
month = "5",
day = "13",
doi = "10.1145/3308558.3313715",
language = "English",
series = "The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019",
publisher = "Association for Computing Machinery, Inc",
pages = "470--479",
booktitle = "The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019",

}

Feng, MH, Hsu, CC, Li, C-T, Yeh, MY & Lin, SD 2019, Marine: Multi-relational network embeddings with relational proximity and node attributes. in The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019. The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019, Association for Computing Machinery, Inc, pp. 470-479, 2019 World Wide Web Conference, WWW 2019, San Francisco, United States, 19-05-13. https://doi.org/10.1145/3308558.3313715

Marine : Multi-relational network embeddings with relational proximity and node attributes. / Feng, Ming Han; Hsu, Chin Chi; Li, Cheng-Te; Yeh, Mi Yen; Lin, Shou De.

The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019. Association for Computing Machinery, Inc, 2019. p. 470-479 (The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019).

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

TY - GEN

T1 - Marine

T2 - Multi-relational network embeddings with relational proximity and node attributes

AU - Feng, Ming Han

AU - Hsu, Chin Chi

AU - Li, Cheng-Te

AU - Yeh, Mi Yen

AU - Lin, Shou De

PY - 2019/5/13

Y1 - 2019/5/13

N2 - Network embedding aims at learning an effective vector transformation for entities in a network. We observe that there are two diverse branches of network embedding: for homogeneous graphs and for multi-relational graphs. This paper then proposes MARINE, a unified embedding framework for both homogeneous and multi-relational networks to preserve both the proximity and relation information. We also extend the framework to incorporate existing features of nodes in a graph, which can further be exploited for the ensemble of embedding. Our solution possesses complexity linear to the number of edges, which is suitable for large-scale network applications. Experiments conducted on several real-world network datasets, along with applications in link prediction and multi-label classification, exhibit the superiority of our proposed MARINE.

AB - Network embedding aims at learning an effective vector transformation for entities in a network. We observe that there are two diverse branches of network embedding: for homogeneous graphs and for multi-relational graphs. This paper then proposes MARINE, a unified embedding framework for both homogeneous and multi-relational networks to preserve both the proximity and relation information. We also extend the framework to incorporate existing features of nodes in a graph, which can further be exploited for the ensemble of embedding. Our solution possesses complexity linear to the number of edges, which is suitable for large-scale network applications. Experiments conducted on several real-world network datasets, along with applications in link prediction and multi-label classification, exhibit the superiority of our proposed MARINE.

UR - http://www.scopus.com/inward/record.url?scp=85066903914&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066903914&partnerID=8YFLogxK

U2 - 10.1145/3308558.3313715

DO - 10.1145/3308558.3313715

M3 - Conference contribution

T3 - The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019

SP - 470

EP - 479

BT - The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019

PB - Association for Computing Machinery, Inc

ER -

Feng MH, Hsu CC, Li C-T, Yeh MY, Lin SD. Marine: Multi-relational network embeddings with relational proximity and node attributes. In The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019. Association for Computing Machinery, Inc. 2019. p. 470-479. (The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019). https://doi.org/10.1145/3308558.3313715