Binarized attributed network embedding

Hong Yang, Shirui Pan, Peng Zhang, Ling Chen, Defu Lian, Chengqi Zhang

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

Abstract

Attributed network embedding enables joint representation learning of node links and attributes. Existing attributed network embedding models are designed in continuous Euclidean spaces which often introduce data redundancy and impose challenges to storage and computation costs. To this end, we present a Binarized Attributed Network Embedding model (BANE for short) to learn binary node representation. Specifically, we define a new Weisfeiler-Lehman proximity matrix to capture data dependence between node links and attributes by aggregating the information of node attributes and links from neighboring nodes to a given target node in a layer-wise manner. Based on the Weisfeiler-Lehman proximity matrix, we formulate a new Weisfiler-Lehman matrix factorization learning function under the binary node representation constraint. The learning problem is a mixed integer optimization and an efficient cyclic coordinate descent (CCD) algorithm is used as the solution. Node classification and link prediction experiments on real-world datasets show that the proposed BANE model outperforms the state-of-the-art network embedding methods.

Original languageEnglish
Title of host publicationProceedings - 18th IEEE International Conference on Data Mining Workshops, ICDM 2018
Subtitle of host publication17–20 November 2018 Singapore
EditorsDacheng Tao, Bhavani Thuraisingham
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages1476-1481
Number of pages6
ISBN (Electronic)9781538691595, 9781538691588
ISBN (Print)9781538691601
DOIs
Publication statusPublished - 2018
Externally publishedYes
EventIEEE International Conference on Data Mining 2018 - Singapore, Singapore
Duration: 17 Nov 201820 Nov 2018
http://icdm2018.org/

Conference

ConferenceIEEE International Conference on Data Mining 2018
Abbreviated titleICDM 2018
CountrySingapore
CitySingapore
Period17/11/1820/11/18
Internet address

Keywords

  • Attributed network embedding
  • Learning to hash
  • Weisfeiler-Lehman graph kernels

Cite this

Yang, H., Pan, S., Zhang, P., Chen, L., Lian, D., & Zhang, C. (2018). Binarized attributed network embedding. In D. Tao, & B. Thuraisingham (Eds.), Proceedings - 18th IEEE International Conference on Data Mining Workshops, ICDM 2018: 17–20 November 2018 Singapore (pp. 1476-1481). [8626170] Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ICDM.2018.8626170
Yang, Hong ; Pan, Shirui ; Zhang, Peng ; Chen, Ling ; Lian, Defu ; Zhang, Chengqi. / Binarized attributed network embedding. Proceedings - 18th IEEE International Conference on Data Mining Workshops, ICDM 2018: 17–20 November 2018 Singapore. editor / Dacheng Tao ; Bhavani Thuraisingham. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2018. pp. 1476-1481
@inproceedings{dfed838b45b14b4da031fa69eb053e95,
title = "Binarized attributed network embedding",
abstract = "Attributed network embedding enables joint representation learning of node links and attributes. Existing attributed network embedding models are designed in continuous Euclidean spaces which often introduce data redundancy and impose challenges to storage and computation costs. To this end, we present a Binarized Attributed Network Embedding model (BANE for short) to learn binary node representation. Specifically, we define a new Weisfeiler-Lehman proximity matrix to capture data dependence between node links and attributes by aggregating the information of node attributes and links from neighboring nodes to a given target node in a layer-wise manner. Based on the Weisfeiler-Lehman proximity matrix, we formulate a new Weisfiler-Lehman matrix factorization learning function under the binary node representation constraint. The learning problem is a mixed integer optimization and an efficient cyclic coordinate descent (CCD) algorithm is used as the solution. Node classification and link prediction experiments on real-world datasets show that the proposed BANE model outperforms the state-of-the-art network embedding methods.",
keywords = "Attributed network embedding, Learning to hash, Weisfeiler-Lehman graph kernels",
author = "Hong Yang and Shirui Pan and Peng Zhang and Ling Chen and Defu Lian and Chengqi Zhang",
year = "2018",
doi = "10.1109/ICDM.2018.8626170",
language = "English",
isbn = "9781538691601",
pages = "1476--1481",
editor = "Tao, {Dacheng } and Thuraisingham, {Bhavani }",
booktitle = "Proceedings - 18th IEEE International Conference on Data Mining Workshops, ICDM 2018",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States of America",

}

Yang, H, Pan, S, Zhang, P, Chen, L, Lian, D & Zhang, C 2018, Binarized attributed network embedding. in D Tao & B Thuraisingham (eds), Proceedings - 18th IEEE International Conference on Data Mining Workshops, ICDM 2018: 17–20 November 2018 Singapore., 8626170, IEEE, Institute of Electrical and Electronics Engineers, Piscataway NJ USA, pp. 1476-1481, IEEE International Conference on Data Mining 2018, Singapore, Singapore, 17/11/18. https://doi.org/10.1109/ICDM.2018.8626170

Binarized attributed network embedding. / Yang, Hong; Pan, Shirui; Zhang, Peng; Chen, Ling; Lian, Defu; Zhang, Chengqi.

Proceedings - 18th IEEE International Conference on Data Mining Workshops, ICDM 2018: 17–20 November 2018 Singapore. ed. / Dacheng Tao; Bhavani Thuraisingham. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2018. p. 1476-1481 8626170.

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

TY - GEN

T1 - Binarized attributed network embedding

AU - Yang, Hong

AU - Pan, Shirui

AU - Zhang, Peng

AU - Chen, Ling

AU - Lian, Defu

AU - Zhang, Chengqi

PY - 2018

Y1 - 2018

N2 - Attributed network embedding enables joint representation learning of node links and attributes. Existing attributed network embedding models are designed in continuous Euclidean spaces which often introduce data redundancy and impose challenges to storage and computation costs. To this end, we present a Binarized Attributed Network Embedding model (BANE for short) to learn binary node representation. Specifically, we define a new Weisfeiler-Lehman proximity matrix to capture data dependence between node links and attributes by aggregating the information of node attributes and links from neighboring nodes to a given target node in a layer-wise manner. Based on the Weisfeiler-Lehman proximity matrix, we formulate a new Weisfiler-Lehman matrix factorization learning function under the binary node representation constraint. The learning problem is a mixed integer optimization and an efficient cyclic coordinate descent (CCD) algorithm is used as the solution. Node classification and link prediction experiments on real-world datasets show that the proposed BANE model outperforms the state-of-the-art network embedding methods.

AB - Attributed network embedding enables joint representation learning of node links and attributes. Existing attributed network embedding models are designed in continuous Euclidean spaces which often introduce data redundancy and impose challenges to storage and computation costs. To this end, we present a Binarized Attributed Network Embedding model (BANE for short) to learn binary node representation. Specifically, we define a new Weisfeiler-Lehman proximity matrix to capture data dependence between node links and attributes by aggregating the information of node attributes and links from neighboring nodes to a given target node in a layer-wise manner. Based on the Weisfeiler-Lehman proximity matrix, we formulate a new Weisfiler-Lehman matrix factorization learning function under the binary node representation constraint. The learning problem is a mixed integer optimization and an efficient cyclic coordinate descent (CCD) algorithm is used as the solution. Node classification and link prediction experiments on real-world datasets show that the proposed BANE model outperforms the state-of-the-art network embedding methods.

KW - Attributed network embedding

KW - Learning to hash

KW - Weisfeiler-Lehman graph kernels

UR - http://www.scopus.com/inward/record.url?scp=85061386533&partnerID=8YFLogxK

U2 - 10.1109/ICDM.2018.8626170

DO - 10.1109/ICDM.2018.8626170

M3 - Conference Paper

SN - 9781538691601

SP - 1476

EP - 1481

BT - Proceedings - 18th IEEE International Conference on Data Mining Workshops, ICDM 2018

A2 - Tao, Dacheng

A2 - Thuraisingham, Bhavani

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Piscataway NJ USA

ER -

Yang H, Pan S, Zhang P, Chen L, Lian D, Zhang C. Binarized attributed network embedding. In Tao D, Thuraisingham B, editors, Proceedings - 18th IEEE International Conference on Data Mining Workshops, ICDM 2018: 17–20 November 2018 Singapore. Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. 2018. p. 1476-1481. 8626170 https://doi.org/10.1109/ICDM.2018.8626170