Finding missing edges and communities in incomplete networks

TL;DR

This paper compares algorithms for predicting missing edges in incomplete networks, especially those missing edges typical of real-world data, and examines how such missing data impacts community detection.

Contribution

It introduces a focus on realistic missing edge patterns and evaluates their effect on edge prediction and community detection algorithms.

Findings

Algorithms vary in effectiveness for realistic missing edges

Missing data significantly affects community detection accuracy

Certain algorithms better handle real-world missing edge patterns

Abstract

Many algorithms have been proposed for predicting missing edges in networks, but they do not usually take account of which edges are missing. We focus on networks which have missing edges of the form that is likely to occur in real networks, and compare algorithms that find these missing edges. We also investigate the effect of this kind of missing data on community detection algorithms.