Predicting link directions via a recursive subgraph-based ranking

TL;DR

This paper introduces a recursive subgraph-based ranking method to predict link directions in directed networks, leveraging local and global indicators to improve accuracy over existing methods.

Contribution

It presents a novel recursive ranking approach that combines local subgraph analysis with global information for more accurate link direction prediction.

Findings

Outperforms local and global baseline methods

Recovers a substantial fraction of link directions accurately

Effective on real-world network data

Abstract

Link directions are essential to the functionality of networks and their prediction is helpful towards a better knowledge of directed networks from incomplete real-world data. We study the problem of predicting the directions of some links by using the existence and directions of the rest of links. We propose a solution by first ranking nodes in a specific order and then predicting each link as stemming from a lower-ranked node towards a higher-ranked one. The proposed ranking method works recursively by utilizing local indicators on multiple scales, each corresponding to a subgraph extracted from the original network. Experiments on real networks show that the directions of a substantial fraction of links can be correctly recovered by our method, which outperforms either purely local or global methods.