Playing the role of weak clique property in link prediction: A friend recommendation model

TL;DR

This paper introduces a new local friend recommendation index based on the weak clique property in networks, significantly improving link prediction accuracy by leveraging structural network features.

Contribution

It proposes the PWCS-based FR index and MFR index, novel methods that outperform existing local similarity indices in link prediction tasks.

Findings

FR index outperforms CN, AA, and RA indices

PWCS phenomenon explains improved prediction performance

MFR index further enhances link prediction accuracy

Abstract

An important fact in studying the link prediction is that the structural properties of networks have significant impacts on the performance of algorithms. Therefore, how to improve the performance of link prediction with the aid of structural properties of networks is an essential problem. By analyzing many real networks, we find a common structure property: nodes are preferentially linked to the nodes with the weak clique structure (abbreviated as PWCS to simplify descriptions). Based on this PWCS phenomenon, we propose a local friend recommendation (FR) index to facilitate link prediction. Our experiments show that the performance of FR index is generally better than some famous local similarity indices, such as Common Neighbor (CN) index, Adamic-Adar (AA) index and Resource Allocation (RA) index. We then explain why PWCS can give rise to the better performance of FR index in link prediction. Finally, a mixed friend recommendation index (labelled MFR) is proposed by utilizing the PWCS phenomenon, which further improves the accuracy of link prediction.