Embedding-centrality: Generic centrality computation using neural networks

Rami Puzis; Zion Sofer; Dvir Cohen; Matan Hugi

doi:10.1007/978-3-319-73198-8_8

Embedding-centrality: Generic centrality computation using neural networks

Rami Puzis, Zion Sofer, Dvir Cohen, Matan Hugi

Department of Software and Information Systems Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

Deriving vector representations of vertices in graphs, a.k.a. vertex embedding, is an active field of research. Vertex embedding enables the application of relational data mining techniques to network data. Unintended use of vertex embedding unveils a novel generic method for centrality computation using neural networks. The new centrality measure, termed Embedding Centrality, proposed in this paper is defined as the dot product of a vertex and the center of mass of the graph. Simulation results confirm the validity of Embedding Centrality which correlates well with other commonly used centrality measures. Embedding Centrality can be tailored to specific applications by devising the appropriate context for vertex embedding and can facilitate further understanding of supervised and unsupervised learning methods on graph data.

Original language	English
Title of host publication	Springer Proceedings in Complexity
Editors	Sean Cornelius, Kate Coronges, Bruno Goncalves, Roberta Sinatra, Alessandro Vespignani
Publisher	Springer Science and Business Media B.V.
Pages	87-97
Number of pages	11
ISBN (Print)	9783319731971
DOIs	https://doi.org/10.1007/978-3-319-73198-8_8
State	Published - 1 Jan 2018
Event	9th International Conference on Complex Networks, CompleNet 2018 - Boston, United States Duration: 5 Mar 2018 → 8 Mar 2018

Publication series

Name	Springer Proceedings in Complexity
Volume	0
ISSN (Print)	2213-8684
ISSN (Electronic)	2213-8692

Conference

Conference	9th International Conference on Complex Networks, CompleNet 2018
Country/Territory	United States
City	Boston
Period	5/03/18 → 8/03/18

ASJC Scopus subject areas

Applied Mathematics
Modeling and Simulation
Computer Science Applications

Access to Document

10.1007/978-3-319-73198-8_8

Cite this

Puzis, R., Sofer, Z., Cohen, D., & Hugi, M. (2018). Embedding-centrality: Generic centrality computation using neural networks. In S. Cornelius, K. Coronges, B. Goncalves, R. Sinatra, & A. Vespignani (Eds.), Springer Proceedings in Complexity (pp. 87-97). (Springer Proceedings in Complexity; Vol. 0). Springer Science and Business Media B.V.. https://doi.org/10.1007/978-3-319-73198-8_8

@inproceedings{7c8bbdc671e641ab91d681328fe6e378,

title = "Embedding-centrality: Generic centrality computation using neural networks",

abstract = "Deriving vector representations of vertices in graphs, a.k.a. vertex embedding, is an active field of research. Vertex embedding enables the application of relational data mining techniques to network data. Unintended use of vertex embedding unveils a novel generic method for centrality computation using neural networks. The new centrality measure, termed Embedding Centrality, proposed in this paper is defined as the dot product of a vertex and the center of mass of the graph. Simulation results confirm the validity of Embedding Centrality which correlates well with other commonly used centrality measures. Embedding Centrality can be tailored to specific applications by devising the appropriate context for vertex embedding and can facilitate further understanding of supervised and unsupervised learning methods on graph data.",

author = "Rami Puzis and Zion Sofer and Dvir Cohen and Matan Hugi",

note = "Publisher Copyright: {\textcopyright} Springer International Publishing AG 2018.; 9th International Conference on Complex Networks, CompleNet 2018 ; Conference date: 05-03-2018 Through 08-03-2018",

year = "2018",

month = jan,

day = "1",

doi = "10.1007/978-3-319-73198-8_8",

language = "English",

isbn = "9783319731971",

series = "Springer Proceedings in Complexity",

publisher = "Springer Science and Business Media B.V.",

pages = "87--97",

editor = "Sean Cornelius and Kate Coronges and Bruno Goncalves and Roberta Sinatra and Alessandro Vespignani",

booktitle = "Springer Proceedings in Complexity",

address = "Germany",

}

Puzis, R, Sofer, Z, Cohen, D & Hugi, M 2018, Embedding-centrality: Generic centrality computation using neural networks. in S Cornelius, K Coronges, B Goncalves, R Sinatra & A Vespignani (eds), Springer Proceedings in Complexity. Springer Proceedings in Complexity, vol. 0, Springer Science and Business Media B.V., pp. 87-97, 9th International Conference on Complex Networks, CompleNet 2018, Boston, United States, 5/03/18. https://doi.org/10.1007/978-3-319-73198-8_8

Embedding-centrality: Generic centrality computation using neural networks. / Puzis, Rami; Sofer, Zion; Cohen, Dvir et al.
Springer Proceedings in Complexity. ed. / Sean Cornelius; Kate Coronges; Bruno Goncalves; Roberta Sinatra; Alessandro Vespignani. Springer Science and Business Media B.V., 2018. p. 87-97 (Springer Proceedings in Complexity; Vol. 0).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Embedding-centrality

T2 - 9th International Conference on Complex Networks, CompleNet 2018

AU - Puzis, Rami

AU - Sofer, Zion

AU - Cohen, Dvir

AU - Hugi, Matan

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Deriving vector representations of vertices in graphs, a.k.a. vertex embedding, is an active field of research. Vertex embedding enables the application of relational data mining techniques to network data. Unintended use of vertex embedding unveils a novel generic method for centrality computation using neural networks. The new centrality measure, termed Embedding Centrality, proposed in this paper is defined as the dot product of a vertex and the center of mass of the graph. Simulation results confirm the validity of Embedding Centrality which correlates well with other commonly used centrality measures. Embedding Centrality can be tailored to specific applications by devising the appropriate context for vertex embedding and can facilitate further understanding of supervised and unsupervised learning methods on graph data.

AB - Deriving vector representations of vertices in graphs, a.k.a. vertex embedding, is an active field of research. Vertex embedding enables the application of relational data mining techniques to network data. Unintended use of vertex embedding unveils a novel generic method for centrality computation using neural networks. The new centrality measure, termed Embedding Centrality, proposed in this paper is defined as the dot product of a vertex and the center of mass of the graph. Simulation results confirm the validity of Embedding Centrality which correlates well with other commonly used centrality measures. Embedding Centrality can be tailored to specific applications by devising the appropriate context for vertex embedding and can facilitate further understanding of supervised and unsupervised learning methods on graph data.

UR - http://www.scopus.com/inward/record.url?scp=85054728420&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-73198-8_8

DO - 10.1007/978-3-319-73198-8_8

M3 - Conference contribution

AN - SCOPUS:85054728420

SN - 9783319731971

T3 - Springer Proceedings in Complexity

SP - 87

EP - 97

BT - Springer Proceedings in Complexity

A2 - Cornelius, Sean

A2 - Coronges, Kate

A2 - Goncalves, Bruno

A2 - Sinatra, Roberta

A2 - Vespignani, Alessandro

PB - Springer Science and Business Media B.V.

Y2 - 5 March 2018 through 8 March 2018

ER -

Embedding-centrality: Generic centrality computation using neural networks

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this