Abstract

Nowadays, people usually participate in multiple social networks simultaneously, e.g., Facebook and Twitter. Formally, the correspondences of the accounts that belong to the same user are defined as anchor links, and the networks aligned by anchor links can be denoted as aligned networks. In this paper, we study the problem of anchor link prediction (ALP) across a pair of aligned networks based on social network structure. First, three similarity metrics (CPS, CCS, and CPS+) are proposed. Different from the previous works, we focus on the theoretical guarantees of our metrics. We prove mathematically that the node pair with the maximum CPS or CPS+ should be an anchor link with high probability and a correctly predicted anchor link must have a high value of CCS. Second, using the CPS+ and CCS, we present a two-stage iterative algorithm CPCC to solve the problem of the ALP. More specifically, we present an early termination strategy to make a tradeoff between precision and recall. At last, a series of experiments are conducted on both synthetic and real-world social networks to demonstrate the effectiveness of the CPCC.

Original languageEnglish (US)
Pages (from-to)17340-17353
Number of pages14
JournalIEEE Access
Volume6
DOIs
StatePublished - Mar 8 2018

Fingerprint

Anchors
Experiments

Keywords

  • aligned networks
  • Anchor link prediction
  • similarity metric
  • social network

ASJC Scopus subject areas

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)

Cite this

Inferring Anchor Links Based on Social Network Structure. / Feng, Shuo; Shen, Derong; Nie, Tiezheng; Kou, Yue; He, Jingrui; Yu, Ge.

In: IEEE Access, Vol. 6, 08.03.2018, p. 17340-17353.

Research output: Contribution to journalArticle

Feng, S, Shen, D, Nie, T, Kou, Y, He, J & Yu, G 2018, 'Inferring Anchor Links Based on Social Network Structure', IEEE Access, vol. 6, pp. 17340-17353. https://doi.org/10.1109/ACCESS.2018.2814000
Feng, Shuo ; Shen, Derong ; Nie, Tiezheng ; Kou, Yue ; He, Jingrui ; Yu, Ge. / Inferring Anchor Links Based on Social Network Structure. In: IEEE Access. 2018 ; Vol. 6. pp. 17340-17353.
@article{645572bebd3f46fca8eec68ebddbae23,
title = "Inferring Anchor Links Based on Social Network Structure",
abstract = "Nowadays, people usually participate in multiple social networks simultaneously, e.g., Facebook and Twitter. Formally, the correspondences of the accounts that belong to the same user are defined as anchor links, and the networks aligned by anchor links can be denoted as aligned networks. In this paper, we study the problem of anchor link prediction (ALP) across a pair of aligned networks based on social network structure. First, three similarity metrics (CPS, CCS, and CPS+) are proposed. Different from the previous works, we focus on the theoretical guarantees of our metrics. We prove mathematically that the node pair with the maximum CPS or CPS+ should be an anchor link with high probability and a correctly predicted anchor link must have a high value of CCS. Second, using the CPS+ and CCS, we present a two-stage iterative algorithm CPCC to solve the problem of the ALP. More specifically, we present an early termination strategy to make a tradeoff between precision and recall. At last, a series of experiments are conducted on both synthetic and real-world social networks to demonstrate the effectiveness of the CPCC.",
keywords = "aligned networks, Anchor link prediction, similarity metric, social network",
author = "Shuo Feng and Derong Shen and Tiezheng Nie and Yue Kou and Jingrui He and Ge Yu",
year = "2018",
month = "3",
day = "8",
doi = "10.1109/ACCESS.2018.2814000",
language = "English (US)",
volume = "6",
pages = "17340--17353",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Inferring Anchor Links Based on Social Network Structure

AU - Feng, Shuo

AU - Shen, Derong

AU - Nie, Tiezheng

AU - Kou, Yue

AU - He, Jingrui

AU - Yu, Ge

PY - 2018/3/8

Y1 - 2018/3/8

N2 - Nowadays, people usually participate in multiple social networks simultaneously, e.g., Facebook and Twitter. Formally, the correspondences of the accounts that belong to the same user are defined as anchor links, and the networks aligned by anchor links can be denoted as aligned networks. In this paper, we study the problem of anchor link prediction (ALP) across a pair of aligned networks based on social network structure. First, three similarity metrics (CPS, CCS, and CPS+) are proposed. Different from the previous works, we focus on the theoretical guarantees of our metrics. We prove mathematically that the node pair with the maximum CPS or CPS+ should be an anchor link with high probability and a correctly predicted anchor link must have a high value of CCS. Second, using the CPS+ and CCS, we present a two-stage iterative algorithm CPCC to solve the problem of the ALP. More specifically, we present an early termination strategy to make a tradeoff between precision and recall. At last, a series of experiments are conducted on both synthetic and real-world social networks to demonstrate the effectiveness of the CPCC.

AB - Nowadays, people usually participate in multiple social networks simultaneously, e.g., Facebook and Twitter. Formally, the correspondences of the accounts that belong to the same user are defined as anchor links, and the networks aligned by anchor links can be denoted as aligned networks. In this paper, we study the problem of anchor link prediction (ALP) across a pair of aligned networks based on social network structure. First, three similarity metrics (CPS, CCS, and CPS+) are proposed. Different from the previous works, we focus on the theoretical guarantees of our metrics. We prove mathematically that the node pair with the maximum CPS or CPS+ should be an anchor link with high probability and a correctly predicted anchor link must have a high value of CCS. Second, using the CPS+ and CCS, we present a two-stage iterative algorithm CPCC to solve the problem of the ALP. More specifically, we present an early termination strategy to make a tradeoff between precision and recall. At last, a series of experiments are conducted on both synthetic and real-world social networks to demonstrate the effectiveness of the CPCC.

KW - aligned networks

KW - Anchor link prediction

KW - similarity metric

KW - social network

UR - http://www.scopus.com/inward/record.url?scp=85043474439&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85043474439&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2018.2814000

DO - 10.1109/ACCESS.2018.2814000

M3 - Article

VL - 6

SP - 17340

EP - 17353

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

ER -