A Scalable Proximity Measure for Link Prediction via Low-rank Matrix Estimation

DOI

10.2991/csss-14.2014.1How to use a DOI?

Keywords

link prediction; social network; proximity measure; low-rank estimation; data mining

Abstract

Recent years, the link prediction problem in social network and other complex networks become a popular research field. One of the most significant task in link prediction is to design the proximity measure to calculate the similarities of the nodes in the network. The potential structure of the networks in the link prediction problem can be learned from the network data. In this paper, we propose a data-dependent proximity measure under the low-rank assumption in the social network and many other complex networks, then design a scalable matrix estimation algorithm to figure out the proximity measure. According to our experiment results, the proposed proximity measure can get competitive performance compared with other state-of-the-art methods and can be scalable for complex network link prediction.

Copyright

© 2014, 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  - Liu Ye
AU  - Wang Zhisheng
AU  - Yin Jian
AU  - Pan Yan
PY  - 2014/06
DA  - 2014/06
TI  - A Scalable Proximity Measure for Link Prediction via Low-rank Matrix Estimation
BT  - Proceedings of the 3rd International Conference on Computer Science and Service System
PB  - Atlantis Press
SP  - 1
EP  - 4
SN  - 1951-6851
UR  - https://doi.org/10.2991/csss-14.2014.1
DO  - 10.2991/csss-14.2014.1
ID  - Ye2014/06
ER  -