Scalable manifold-regularized attributed network embedding via maximum mean discrepancy

Jun Wu, Jingrui He

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

Abstract

Networks are ubiquitous in many real-world applications due to their capability of representing the rich information in the data. One fundamental problem of network analysis is to learn a low-dimensional vector representation for nodes within the attributed networks. However, there is little work theoretically considering the information heterogeneity from the attributed networks, and most of the existing attributed network embedding techniques are able to capture at most kth order node proximity, thus leading to the information loss of the long-range spatial dependencies between individual nodes across the entire network. To address the above problems, in this paper, we propose a novel MAnifold-RegularIzed Network Embedding (MARINE) algorithm inspired by minimizing the information discrepancy in a Reproducing Kernel Hilbert Space via Maximum Mean Discrepancy. In particular, we show that MARINE recursively aggregates the graph structure information as well as individual node attributes from the entire network, and thereby preserves the long-range spatial dependencies between nodes across the network. The experimental results on real networks demonstrate the effectiveness and efficiency of the proposed MARINE algorithm over state-of-the-art embedding methods.

Original languageEnglish (US)
Title of host publicationCIKM 2019 - Proceedings of the 28th ACM International Conference on Information and Knowledge Management
PublisherAssociation for Computing Machinery
Pages2101-2104
Number of pages4
ISBN (Electronic)9781450369763
DOIs
StatePublished - Nov 3 2019
Event28th ACM International Conference on Information and Knowledge Management, CIKM 2019 - Beijing, China
Duration: Nov 3 2019Nov 7 2019

Publication series

NameInternational Conference on Information and Knowledge Management, Proceedings

Conference

Conference28th ACM International Conference on Information and Knowledge Management, CIKM 2019
CountryChina
CityBeijing
Period11/3/1911/7/19

Fingerprint

Discrepancy
Node
Kernel
Hilbert space
Proximity
Information structure
Network analysis
Graph

Keywords

  • Embedding
  • Manifold Regularization
  • Maximum Mean Discrepancy

ASJC Scopus subject areas

  • Business, Management and Accounting(all)
  • Decision Sciences(all)

Cite this

Wu, J., & He, J. (2019). Scalable manifold-regularized attributed network embedding via maximum mean discrepancy. In CIKM 2019 - Proceedings of the 28th ACM International Conference on Information and Knowledge Management (pp. 2101-2104). (International Conference on Information and Knowledge Management, Proceedings). Association for Computing Machinery. https://doi.org/10.1145/3357384.3358091

Scalable manifold-regularized attributed network embedding via maximum mean discrepancy. / Wu, Jun; He, Jingrui.

CIKM 2019 - Proceedings of the 28th ACM International Conference on Information and Knowledge Management. Association for Computing Machinery, 2019. p. 2101-2104 (International Conference on Information and Knowledge Management, Proceedings).

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

Wu, J & He, J 2019, Scalable manifold-regularized attributed network embedding via maximum mean discrepancy. in CIKM 2019 - Proceedings of the 28th ACM International Conference on Information and Knowledge Management. International Conference on Information and Knowledge Management, Proceedings, Association for Computing Machinery, pp. 2101-2104, 28th ACM International Conference on Information and Knowledge Management, CIKM 2019, Beijing, China, 11/3/19. https://doi.org/10.1145/3357384.3358091
Wu J, He J. Scalable manifold-regularized attributed network embedding via maximum mean discrepancy. In CIKM 2019 - Proceedings of the 28th ACM International Conference on Information and Knowledge Management. Association for Computing Machinery. 2019. p. 2101-2104. (International Conference on Information and Knowledge Management, Proceedings). https://doi.org/10.1145/3357384.3358091
Wu, Jun ; He, Jingrui. / Scalable manifold-regularized attributed network embedding via maximum mean discrepancy. CIKM 2019 - Proceedings of the 28th ACM International Conference on Information and Knowledge Management. Association for Computing Machinery, 2019. pp. 2101-2104 (International Conference on Information and Knowledge Management, Proceedings).
@inproceedings{844daab6ff214d7aa134db59665a2a77,
title = "Scalable manifold-regularized attributed network embedding via maximum mean discrepancy",
abstract = "Networks are ubiquitous in many real-world applications due to their capability of representing the rich information in the data. One fundamental problem of network analysis is to learn a low-dimensional vector representation for nodes within the attributed networks. However, there is little work theoretically considering the information heterogeneity from the attributed networks, and most of the existing attributed network embedding techniques are able to capture at most kth order node proximity, thus leading to the information loss of the long-range spatial dependencies between individual nodes across the entire network. To address the above problems, in this paper, we propose a novel MAnifold-RegularIzed Network Embedding (MARINE) algorithm inspired by minimizing the information discrepancy in a Reproducing Kernel Hilbert Space via Maximum Mean Discrepancy. In particular, we show that MARINE recursively aggregates the graph structure information as well as individual node attributes from the entire network, and thereby preserves the long-range spatial dependencies between nodes across the network. The experimental results on real networks demonstrate the effectiveness and efficiency of the proposed MARINE algorithm over state-of-the-art embedding methods.",
keywords = "Embedding, Manifold Regularization, Maximum Mean Discrepancy",
author = "Jun Wu and Jingrui He",
year = "2019",
month = "11",
day = "3",
doi = "10.1145/3357384.3358091",
language = "English (US)",
series = "International Conference on Information and Knowledge Management, Proceedings",
publisher = "Association for Computing Machinery",
pages = "2101--2104",
booktitle = "CIKM 2019 - Proceedings of the 28th ACM International Conference on Information and Knowledge Management",

}

TY - GEN

T1 - Scalable manifold-regularized attributed network embedding via maximum mean discrepancy

AU - Wu, Jun

AU - He, Jingrui

PY - 2019/11/3

Y1 - 2019/11/3

N2 - Networks are ubiquitous in many real-world applications due to their capability of representing the rich information in the data. One fundamental problem of network analysis is to learn a low-dimensional vector representation for nodes within the attributed networks. However, there is little work theoretically considering the information heterogeneity from the attributed networks, and most of the existing attributed network embedding techniques are able to capture at most kth order node proximity, thus leading to the information loss of the long-range spatial dependencies between individual nodes across the entire network. To address the above problems, in this paper, we propose a novel MAnifold-RegularIzed Network Embedding (MARINE) algorithm inspired by minimizing the information discrepancy in a Reproducing Kernel Hilbert Space via Maximum Mean Discrepancy. In particular, we show that MARINE recursively aggregates the graph structure information as well as individual node attributes from the entire network, and thereby preserves the long-range spatial dependencies between nodes across the network. The experimental results on real networks demonstrate the effectiveness and efficiency of the proposed MARINE algorithm over state-of-the-art embedding methods.

AB - Networks are ubiquitous in many real-world applications due to their capability of representing the rich information in the data. One fundamental problem of network analysis is to learn a low-dimensional vector representation for nodes within the attributed networks. However, there is little work theoretically considering the information heterogeneity from the attributed networks, and most of the existing attributed network embedding techniques are able to capture at most kth order node proximity, thus leading to the information loss of the long-range spatial dependencies between individual nodes across the entire network. To address the above problems, in this paper, we propose a novel MAnifold-RegularIzed Network Embedding (MARINE) algorithm inspired by minimizing the information discrepancy in a Reproducing Kernel Hilbert Space via Maximum Mean Discrepancy. In particular, we show that MARINE recursively aggregates the graph structure information as well as individual node attributes from the entire network, and thereby preserves the long-range spatial dependencies between nodes across the network. The experimental results on real networks demonstrate the effectiveness and efficiency of the proposed MARINE algorithm over state-of-the-art embedding methods.

KW - Embedding

KW - Manifold Regularization

KW - Maximum Mean Discrepancy

UR - http://www.scopus.com/inward/record.url?scp=85075423038&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85075423038&partnerID=8YFLogxK

U2 - 10.1145/3357384.3358091

DO - 10.1145/3357384.3358091

M3 - Conference contribution

AN - SCOPUS:85075423038

T3 - International Conference on Information and Knowledge Management, Proceedings

SP - 2101

EP - 2104

BT - CIKM 2019 - Proceedings of the 28th ACM International Conference on Information and Knowledge Management

PB - Association for Computing Machinery

ER -