Issue |
EPL
Volume 117, Number 3, February 2017
|
|
---|---|---|
Article Number | 38002 | |
Number of page(s) | 7 | |
Section | Interdisciplinary Physics and Related Areas of Science and Technology | |
DOI | https://doi.org/10.1209/0295-5075/117/38002 | |
Published online | 22 March 2017 |
Link prediction via matrix completion
1 CompleX Lab, University of Electronic Science and Technology of China - Chengdu 611731, PRC
2 Big Data Research Center, University of Electronic Science and Technology of China - Chengdu 611731, PRC
3 Center for Robotics, University of Electronic Science and Technology of China - Chengdu 611731, PRC
(a) haodong@uestc.edu.cn
(b) zhutou@ustc.edu
Received: 6 June 2016
Accepted: 15 February 2017
Inspired by the practical importance of social networks, economic networks, biological networks and so on, studies on large and complex networks have attracted a surge of attention in the recent years. Link prediction is a fundamental issue to understand the mechanisms by which new links are added to the networks. We introduce the method of robust principal component analysis (robust PCA) into link prediction, and estimate the missing entries of the adjacency matrix. On the one hand, our algorithm is based on the sparse and low-rank property of the matrix, while, on the other hand, it also performs very well when the network is dense. This is because a relatively dense real network is also sparse in comparison to the complete graph. According to extensive experiments on real networks from disparate fields, when the target network is connected and sufficiently dense, whether it is weighted or unweighted, our method is demonstrated to be very effective and with prediction accuracy being considerably improved compared to many state-of-the-art algorithms.
PACS: 89.65.-s – Social and economic systems / 89.20.Ff – Computer science and technology / 89.75.Hc – Networks and genealogical trees
© EPLA, 2017
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.