MATRI: A multi-aspect and transitive trust inference model

Yuan Yao, Hanghang Tong, Xifeng Yan, Feng Xu, Jian Lu

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

29 Citations (Scopus)

Abstract

Trust inference, which is the mechanism to build new pair-wise trustworthiness relationship based on the existing ones, is a fundamental integral part in many real applications, e.g., e-commerce, social networks, peer-to-peer networks, etc. State-of-the-art trust inference approaches mainly employ the transitivity property of trust by propagating trust along connected users (a.k.a. trust propagation), but largely ignore other important properties, e.g., prior knowledge, multi-aspect, etc. In this paper, we propose a multi-aspect trust inference model by exploring an equally important property of trust, i.e., the multi-aspect property. The heart of our method is to view the problem as a recommendation problem, and hence opens the door to the rich methodologies in the field of collaborative filtering. The proposed multi-aspect model directly characterizes multiple latent factors for each trustor and trustee from the locally-generated trust relationships. Moreover, we extend this model to incorporate the prior knowledge as well as trust propagation to further improve inference accuracy. We conduct extensive experimental evaluations on real data sets, which demonstrate that our method achieves significant improvement over several existing benchmark approaches. Overall, the proposed method (MATRI) leads to 26.7% - 40.7% improvement over its best known competitors in prediction accuracy; and up to 7 orders of magnitude speedup with linear scalability. Copyright is held by the International World Wide Web Conference Committee (IW3C2).

Original languageEnglish (US)
Title of host publicationWWW 2013 - Proceedings of the 22nd International Conference on World Wide Web
Pages1467-1476
Number of pages10
StatePublished - 2013
Externally publishedYes
Event22nd International Conference on World Wide Web, WWW 2013 - Rio de Janeiro, Brazil
Duration: May 13 2013May 17 2013

Other

Other22nd International Conference on World Wide Web, WWW 2013
CountryBrazil
CityRio de Janeiro
Period5/13/135/17/13

Fingerprint

Collaborative filtering
Peer to peer networks
World Wide Web
Scalability

Keywords

  • Latent factors
  • Multi-aspect property
  • Prior knowledge
  • Transitivity property
  • Trust inference

ASJC Scopus subject areas

  • Computer Networks and Communications

Cite this

Yao, Y., Tong, H., Yan, X., Xu, F., & Lu, J. (2013). MATRI: A multi-aspect and transitive trust inference model. In WWW 2013 - Proceedings of the 22nd International Conference on World Wide Web (pp. 1467-1476)

MATRI : A multi-aspect and transitive trust inference model. / Yao, Yuan; Tong, Hanghang; Yan, Xifeng; Xu, Feng; Lu, Jian.

WWW 2013 - Proceedings of the 22nd International Conference on World Wide Web. 2013. p. 1467-1476.

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

Yao, Y, Tong, H, Yan, X, Xu, F & Lu, J 2013, MATRI: A multi-aspect and transitive trust inference model. in WWW 2013 - Proceedings of the 22nd International Conference on World Wide Web. pp. 1467-1476, 22nd International Conference on World Wide Web, WWW 2013, Rio de Janeiro, Brazil, 5/13/13.
Yao Y, Tong H, Yan X, Xu F, Lu J. MATRI: A multi-aspect and transitive trust inference model. In WWW 2013 - Proceedings of the 22nd International Conference on World Wide Web. 2013. p. 1467-1476
Yao, Yuan ; Tong, Hanghang ; Yan, Xifeng ; Xu, Feng ; Lu, Jian. / MATRI : A multi-aspect and transitive trust inference model. WWW 2013 - Proceedings of the 22nd International Conference on World Wide Web. 2013. pp. 1467-1476
@inproceedings{0719fad9cc294a9b89ae5da2ddfc035f,
title = "MATRI: A multi-aspect and transitive trust inference model",
abstract = "Trust inference, which is the mechanism to build new pair-wise trustworthiness relationship based on the existing ones, is a fundamental integral part in many real applications, e.g., e-commerce, social networks, peer-to-peer networks, etc. State-of-the-art trust inference approaches mainly employ the transitivity property of trust by propagating trust along connected users (a.k.a. trust propagation), but largely ignore other important properties, e.g., prior knowledge, multi-aspect, etc. In this paper, we propose a multi-aspect trust inference model by exploring an equally important property of trust, i.e., the multi-aspect property. The heart of our method is to view the problem as a recommendation problem, and hence opens the door to the rich methodologies in the field of collaborative filtering. The proposed multi-aspect model directly characterizes multiple latent factors for each trustor and trustee from the locally-generated trust relationships. Moreover, we extend this model to incorporate the prior knowledge as well as trust propagation to further improve inference accuracy. We conduct extensive experimental evaluations on real data sets, which demonstrate that our method achieves significant improvement over several existing benchmark approaches. Overall, the proposed method (MATRI) leads to 26.7{\%} - 40.7{\%} improvement over its best known competitors in prediction accuracy; and up to 7 orders of magnitude speedup with linear scalability. Copyright is held by the International World Wide Web Conference Committee (IW3C2).",
keywords = "Latent factors, Multi-aspect property, Prior knowledge, Transitivity property, Trust inference",
author = "Yuan Yao and Hanghang Tong and Xifeng Yan and Feng Xu and Jian Lu",
year = "2013",
language = "English (US)",
isbn = "9781450320351",
pages = "1467--1476",
booktitle = "WWW 2013 - Proceedings of the 22nd International Conference on World Wide Web",

}

TY - GEN

T1 - MATRI

T2 - A multi-aspect and transitive trust inference model

AU - Yao, Yuan

AU - Tong, Hanghang

AU - Yan, Xifeng

AU - Xu, Feng

AU - Lu, Jian

PY - 2013

Y1 - 2013

N2 - Trust inference, which is the mechanism to build new pair-wise trustworthiness relationship based on the existing ones, is a fundamental integral part in many real applications, e.g., e-commerce, social networks, peer-to-peer networks, etc. State-of-the-art trust inference approaches mainly employ the transitivity property of trust by propagating trust along connected users (a.k.a. trust propagation), but largely ignore other important properties, e.g., prior knowledge, multi-aspect, etc. In this paper, we propose a multi-aspect trust inference model by exploring an equally important property of trust, i.e., the multi-aspect property. The heart of our method is to view the problem as a recommendation problem, and hence opens the door to the rich methodologies in the field of collaborative filtering. The proposed multi-aspect model directly characterizes multiple latent factors for each trustor and trustee from the locally-generated trust relationships. Moreover, we extend this model to incorporate the prior knowledge as well as trust propagation to further improve inference accuracy. We conduct extensive experimental evaluations on real data sets, which demonstrate that our method achieves significant improvement over several existing benchmark approaches. Overall, the proposed method (MATRI) leads to 26.7% - 40.7% improvement over its best known competitors in prediction accuracy; and up to 7 orders of magnitude speedup with linear scalability. Copyright is held by the International World Wide Web Conference Committee (IW3C2).

AB - Trust inference, which is the mechanism to build new pair-wise trustworthiness relationship based on the existing ones, is a fundamental integral part in many real applications, e.g., e-commerce, social networks, peer-to-peer networks, etc. State-of-the-art trust inference approaches mainly employ the transitivity property of trust by propagating trust along connected users (a.k.a. trust propagation), but largely ignore other important properties, e.g., prior knowledge, multi-aspect, etc. In this paper, we propose a multi-aspect trust inference model by exploring an equally important property of trust, i.e., the multi-aspect property. The heart of our method is to view the problem as a recommendation problem, and hence opens the door to the rich methodologies in the field of collaborative filtering. The proposed multi-aspect model directly characterizes multiple latent factors for each trustor and trustee from the locally-generated trust relationships. Moreover, we extend this model to incorporate the prior knowledge as well as trust propagation to further improve inference accuracy. We conduct extensive experimental evaluations on real data sets, which demonstrate that our method achieves significant improvement over several existing benchmark approaches. Overall, the proposed method (MATRI) leads to 26.7% - 40.7% improvement over its best known competitors in prediction accuracy; and up to 7 orders of magnitude speedup with linear scalability. Copyright is held by the International World Wide Web Conference Committee (IW3C2).

KW - Latent factors

KW - Multi-aspect property

KW - Prior knowledge

KW - Transitivity property

KW - Trust inference

UR - http://www.scopus.com/inward/record.url?scp=84890644208&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84890644208&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84890644208

SN - 9781450320351

SP - 1467

EP - 1476

BT - WWW 2013 - Proceedings of the 22nd International Conference on World Wide Web

ER -