Discerning edge influence for network embedding

Yaojing Wang, Yuan Yao, Hanghang Tong, Feng Xu, Jian Lu

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

Abstract

Network embedding, which learns the low-dimensional representations of nodes, has gained significant research attention. Despite its superior empirical success, often measured by the prediction performance of downstream tasks (e.g., multi-label classification), it is unclear why a given embedding algorithm outputs the specific node representations, and how the resulting node representations relate to the structure of the input network. In this paper, we propose to discern the edge influence as the first step towards understanding skip-gram basd network embedding methods. For this purpose, we propose an auditing framework Near, whose key part includes two algorithms (Near-add and Near-del) to effectively and efficiently quantify the influence of each edge. Based on the algorithms, we further identify high-influential edges by exploiting the linkage between edge influence and the network structure. Experimental results demonstrate that the proposed algorithms (Near-add and Near-del) are significantly faster (up to 2, 000×) than straightforward methods with little quality loss. Moreover, the proposed framework can efficiently identify the most influential edges for network embedding in the context of downstream prediction task and adversarial attacking.

Original languageEnglish (US)
Title of host publicationCIKM 2019 - Proceedings of the 28th ACM International Conference on Information and Knowledge Management
PublisherAssociation for Computing Machinery
Pages429-438
Number of pages10
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

Node
Prediction
Auditing
Linkage
Network structure

Keywords

  • Edge Influence
  • Network Embedding
  • Network Topological Properties

ASJC Scopus subject areas

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

Cite this

Wang, Y., Yao, Y., Tong, H., Xu, F., & Lu, J. (2019). Discerning edge influence for network embedding. In CIKM 2019 - Proceedings of the 28th ACM International Conference on Information and Knowledge Management (pp. 429-438). (International Conference on Information and Knowledge Management, Proceedings). Association for Computing Machinery. https://doi.org/10.1145/3357384.3358044

Discerning edge influence for network embedding. / Wang, Yaojing; Yao, Yuan; Tong, Hanghang; Xu, Feng; Lu, Jian.

CIKM 2019 - Proceedings of the 28th ACM International Conference on Information and Knowledge Management. Association for Computing Machinery, 2019. p. 429-438 (International Conference on Information and Knowledge Management, Proceedings).

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

Wang, Y, Yao, Y, Tong, H, Xu, F & Lu, J 2019, Discerning edge influence for network embedding. 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. 429-438, 28th ACM International Conference on Information and Knowledge Management, CIKM 2019, Beijing, China, 11/3/19. https://doi.org/10.1145/3357384.3358044
Wang Y, Yao Y, Tong H, Xu F, Lu J. Discerning edge influence for network embedding. In CIKM 2019 - Proceedings of the 28th ACM International Conference on Information and Knowledge Management. Association for Computing Machinery. 2019. p. 429-438. (International Conference on Information and Knowledge Management, Proceedings). https://doi.org/10.1145/3357384.3358044
Wang, Yaojing ; Yao, Yuan ; Tong, Hanghang ; Xu, Feng ; Lu, Jian. / Discerning edge influence for network embedding. CIKM 2019 - Proceedings of the 28th ACM International Conference on Information and Knowledge Management. Association for Computing Machinery, 2019. pp. 429-438 (International Conference on Information and Knowledge Management, Proceedings).
@inproceedings{e17fe00e4f854114a98e21031be9c91f,
title = "Discerning edge influence for network embedding",
abstract = "Network embedding, which learns the low-dimensional representations of nodes, has gained significant research attention. Despite its superior empirical success, often measured by the prediction performance of downstream tasks (e.g., multi-label classification), it is unclear why a given embedding algorithm outputs the specific node representations, and how the resulting node representations relate to the structure of the input network. In this paper, we propose to discern the edge influence as the first step towards understanding skip-gram basd network embedding methods. For this purpose, we propose an auditing framework Near, whose key part includes two algorithms (Near-add and Near-del) to effectively and efficiently quantify the influence of each edge. Based on the algorithms, we further identify high-influential edges by exploiting the linkage between edge influence and the network structure. Experimental results demonstrate that the proposed algorithms (Near-add and Near-del) are significantly faster (up to 2, 000×) than straightforward methods with little quality loss. Moreover, the proposed framework can efficiently identify the most influential edges for network embedding in the context of downstream prediction task and adversarial attacking.",
keywords = "Edge Influence, Network Embedding, Network Topological Properties",
author = "Yaojing Wang and Yuan Yao and Hanghang Tong and Feng Xu and Jian Lu",
year = "2019",
month = "11",
day = "3",
doi = "10.1145/3357384.3358044",
language = "English (US)",
series = "International Conference on Information and Knowledge Management, Proceedings",
publisher = "Association for Computing Machinery",
pages = "429--438",
booktitle = "CIKM 2019 - Proceedings of the 28th ACM International Conference on Information and Knowledge Management",

}

TY - GEN

T1 - Discerning edge influence for network embedding

AU - Wang, Yaojing

AU - Yao, Yuan

AU - Tong, Hanghang

AU - Xu, Feng

AU - Lu, Jian

PY - 2019/11/3

Y1 - 2019/11/3

N2 - Network embedding, which learns the low-dimensional representations of nodes, has gained significant research attention. Despite its superior empirical success, often measured by the prediction performance of downstream tasks (e.g., multi-label classification), it is unclear why a given embedding algorithm outputs the specific node representations, and how the resulting node representations relate to the structure of the input network. In this paper, we propose to discern the edge influence as the first step towards understanding skip-gram basd network embedding methods. For this purpose, we propose an auditing framework Near, whose key part includes two algorithms (Near-add and Near-del) to effectively and efficiently quantify the influence of each edge. Based on the algorithms, we further identify high-influential edges by exploiting the linkage between edge influence and the network structure. Experimental results demonstrate that the proposed algorithms (Near-add and Near-del) are significantly faster (up to 2, 000×) than straightforward methods with little quality loss. Moreover, the proposed framework can efficiently identify the most influential edges for network embedding in the context of downstream prediction task and adversarial attacking.

AB - Network embedding, which learns the low-dimensional representations of nodes, has gained significant research attention. Despite its superior empirical success, often measured by the prediction performance of downstream tasks (e.g., multi-label classification), it is unclear why a given embedding algorithm outputs the specific node representations, and how the resulting node representations relate to the structure of the input network. In this paper, we propose to discern the edge influence as the first step towards understanding skip-gram basd network embedding methods. For this purpose, we propose an auditing framework Near, whose key part includes two algorithms (Near-add and Near-del) to effectively and efficiently quantify the influence of each edge. Based on the algorithms, we further identify high-influential edges by exploiting the linkage between edge influence and the network structure. Experimental results demonstrate that the proposed algorithms (Near-add and Near-del) are significantly faster (up to 2, 000×) than straightforward methods with little quality loss. Moreover, the proposed framework can efficiently identify the most influential edges for network embedding in the context of downstream prediction task and adversarial attacking.

KW - Edge Influence

KW - Network Embedding

KW - Network Topological Properties

UR - http://www.scopus.com/inward/record.url?scp=85075436437&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85075436437&partnerID=8YFLogxK

U2 - 10.1145/3357384.3358044

DO - 10.1145/3357384.3358044

M3 - Conference contribution

AN - SCOPUS:85075436437

T3 - International Conference on Information and Knowledge Management, Proceedings

SP - 429

EP - 438

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

PB - Association for Computing Machinery

ER -