Application of Link Prediction in Temporal Networks

DOI

10.2991/iccia.2012.59How to use a DOI?

Keywords

active factor, complex networks, link prediction, temperal networks,

Abstract

Link prediction is an important research hotspot in complex networks. Correlational studies merely use static topology for prediction, without considering the influence of network dynamic evolutionary process on link prediction. We believe that the links are derived from the evolutionary process of network, and dynamic network topology will contain more information, Moreover, many networks have time attribute naturally, which is apt to combine the similarity of time and structure for link prediction. The paper proposes the concept of active factor using time attribute, to extend the similarity based link prediction framework. Then model and analysis the data of citation network and cooperation network with temporal networks. Design the active factors for both network sand verify the performance of these new indexes. The results shows that the indexes with active factor perform better than structure similarity based indexes.

Copyright

© 2013, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Haihang Xu
AU  - Lijun Zhang
PY  - 2014/05
DA  - 2014/05
TI  - Application of Link Prediction in Temporal Networks
BT  - Proceedings of the 2012 2nd International Conference on Computer and Information Application (ICCIA 2012)
PB  - Atlantis Press
SP  - 241
EP  - 244
SN  - 1951-6851
UR  - https://doi.org/10.2991/iccia.2012.59
DO  - 10.2991/iccia.2012.59
ID  - Xu2014/05
ER  -