Active online learning of trusts in social networks

Hoi To Wai, Anna Scaglione, Amir Leshem

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper considers an online optimization algorithm for actively learning trusts on social networks. We first introduce a DeGroot model for opinion dynamics under the influence of stubborn agents and demonstrate how an observer with estimates of the individuals opinions can actively learn the relative trusts among different agents, by fitting the opinions to the steady state equations of the social system equations. The main contribution of this article is an online algorithm for extracting the trust parameters from streaming data of randomly sampled, noisy opinion estimates. The algorithm is based on the stochastic proximal gradient method and it is proven to converge almost surely. Finally, numerical results are presented to corroborate our findings.

Original languageAmerican English
Title of host publication2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages4139-4143
Number of pages5
ISBN (Electronic)9781479999880
DOIs
StatePublished - 18 May 2016
Externally publishedYes
Event41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Shanghai, China
Duration: 20 Mar 201625 Mar 2016

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2016-May
ISSN (Print)1520-6149

Conference

Conference41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016
Country/TerritoryChina
CityShanghai
Period20/03/1625/03/16

Bibliographical note

Publisher Copyright:
© 2016 IEEE.

Keywords

  • active learning
  • online optimization algorithm
  • social networks
  • system identification

Fingerprint

Dive into the research topics of 'Active online learning of trusts in social networks'. Together they form a unique fingerprint.

Cite this