Local and global information preserved network embedding

Yao Ma; Suhang Wang; Jiliang Tang

doi:10.1109/ASONAM.2018.8508496

Local and global information preserved network embedding

Yao Ma, Suhang Wang, Jiliang Tang

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

2 Scopus citations

Abstract

Networks such as social networks, airplane networks, and citation networks are ubiquitous. To apply advanced machine learning algorithms to network data, low-dimensional and continuous representations are desired. To achieve this goal, many network embedding methods have been proposed recently. The majority of existing methods facilitate the local information i.e. local connections between nodes, to learn the representations, while neglecting global information (or node status), which has been proven to boost numerous network mining tasks such as link prediction and social recommendation. In this paper, we study the problem of preserving local and global information for network embedding. In particular, we introduce an approach to capture global information and propose a network embedding framework LOG, which can coherently model LOcal and Global information. Experiments demonstrate the effectiveness of the proposed framework.

Original language	English (US)
Title of host publication	Proceedings of the 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018
Editors	Andrea Tagarelli, Chandan Reddy, Ulrik Brandes
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	222-225
Number of pages	4
ISBN (Electronic)	9781538660515
DOIs	https://doi.org/10.1109/ASONAM.2018.8508496
State	Published - Oct 24 2018
Externally published	Yes
Event	10th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018 - Barcelona, Spain Duration: Aug 28 2018 → Aug 31 2018

Publication series

Name	Proceedings of the 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018

Conference

Conference	10th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018
Country/Territory	Spain
City	Barcelona
Period	8/28/18 → 8/31/18

All Science Journal Classification (ASJC) codes

Sociology and Political Science
Communication
Computer Networks and Communications
Information Systems and Management

Keywords

embedding
global information
network

Access to Document

10.1109/ASONAM.2018.8508496

Cite this

Ma, Y., Wang, S., & Tang, J. (2018). Local and global information preserved network embedding. In A. Tagarelli, C. Reddy, & U. Brandes (Eds.), Proceedings of the 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018 (pp. 222-225). Article 8508496 (Proceedings of the 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ASONAM.2018.8508496

Ma, Yao ; Wang, Suhang ; Tang, Jiliang. / Local and global information preserved network embedding. Proceedings of the 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018. editor / Andrea Tagarelli ; Chandan Reddy ; Ulrik Brandes. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 222-225 (Proceedings of the 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018).

@inproceedings{0dfbfc7c80894e8999f69bc32f20f875,

title = "Local and global information preserved network embedding",

abstract = "Networks such as social networks, airplane networks, and citation networks are ubiquitous. To apply advanced machine learning algorithms to network data, low-dimensional and continuous representations are desired. To achieve this goal, many network embedding methods have been proposed recently. The majority of existing methods facilitate the local information i.e. local connections between nodes, to learn the representations, while neglecting global information (or node status), which has been proven to boost numerous network mining tasks such as link prediction and social recommendation. In this paper, we study the problem of preserving local and global information for network embedding. In particular, we introduce an approach to capture global information and propose a network embedding framework LOG, which can coherently model LOcal and Global information. Experiments demonstrate the effectiveness of the proposed framework.",

keywords = "embedding, global information, network",

author = "Yao Ma and Suhang Wang and Jiliang Tang",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 10th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018 ; Conference date: 28-08-2018 Through 31-08-2018",

year = "2018",

month = oct,

day = "24",

doi = "10.1109/ASONAM.2018.8508496",

language = "English (US)",

series = "Proceedings of the 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "222--225",

editor = "Andrea Tagarelli and Chandan Reddy and Ulrik Brandes",

booktitle = "Proceedings of the 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018",

address = "United States",

}

Ma, Y, Wang, S & Tang, J 2018, Local and global information preserved network embedding. in A Tagarelli, C Reddy & U Brandes (eds), Proceedings of the 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018., 8508496, Proceedings of the 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018, Institute of Electrical and Electronics Engineers Inc., pp. 222-225, 10th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018, Barcelona, Spain, 8/28/18. https://doi.org/10.1109/ASONAM.2018.8508496

Local and global information preserved network embedding. / Ma, Yao; Wang, Suhang; Tang, Jiliang.
Proceedings of the 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018. ed. / Andrea Tagarelli; Chandan Reddy; Ulrik Brandes. Institute of Electrical and Electronics Engineers Inc., 2018. p. 222-225 8508496 (Proceedings of the 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018).

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

TY - GEN

T1 - Local and global information preserved network embedding

AU - Ma, Yao

AU - Wang, Suhang

AU - Tang, Jiliang

PY - 2018/10/24

Y1 - 2018/10/24

N2 - Networks such as social networks, airplane networks, and citation networks are ubiquitous. To apply advanced machine learning algorithms to network data, low-dimensional and continuous representations are desired. To achieve this goal, many network embedding methods have been proposed recently. The majority of existing methods facilitate the local information i.e. local connections between nodes, to learn the representations, while neglecting global information (or node status), which has been proven to boost numerous network mining tasks such as link prediction and social recommendation. In this paper, we study the problem of preserving local and global information for network embedding. In particular, we introduce an approach to capture global information and propose a network embedding framework LOG, which can coherently model LOcal and Global information. Experiments demonstrate the effectiveness of the proposed framework.

AB - Networks such as social networks, airplane networks, and citation networks are ubiquitous. To apply advanced machine learning algorithms to network data, low-dimensional and continuous representations are desired. To achieve this goal, many network embedding methods have been proposed recently. The majority of existing methods facilitate the local information i.e. local connections between nodes, to learn the representations, while neglecting global information (or node status), which has been proven to boost numerous network mining tasks such as link prediction and social recommendation. In this paper, we study the problem of preserving local and global information for network embedding. In particular, we introduce an approach to capture global information and propose a network embedding framework LOG, which can coherently model LOcal and Global information. Experiments demonstrate the effectiveness of the proposed framework.

KW - embedding

KW - global information

KW - network

UR - http://www.scopus.com/inward/record.url?scp=85057299842&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85057299842&partnerID=8YFLogxK

U2 - 10.1109/ASONAM.2018.8508496

DO - 10.1109/ASONAM.2018.8508496

M3 - Conference contribution

AN - SCOPUS:85057299842

T3 - Proceedings of the 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018

SP - 222

EP - 225

BT - Proceedings of the 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018

A2 - Tagarelli, Andrea

A2 - Reddy, Chandan

A2 - Brandes, Ulrik

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 10th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018

Y2 - 28 August 2018 through 31 August 2018

ER -

Ma Y, Wang S, Tang J. Local and global information preserved network embedding. In Tagarelli A, Reddy C, Brandes U, editors, Proceedings of the 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 222-225. 8508496. (Proceedings of the 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018). doi: 10.1109/ASONAM.2018.8508496

Local and global information preserved network embedding

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this