Handling oversampling in dynamic networks using link prediction

TL;DR

This paper investigates the impact of oversampling noise in dynamic networks on link prediction and introduces a generative model to mitigate its effects, improving prediction quality on synthetic and real data.

Contribution

It presents a novel generative model for oversampling noise and demonstrates how link prediction can be used to recover from oversampling effects in dynamic networks.

Findings

Oversampling negatively impacts link prediction accuracy.

Using link prediction can help recover from oversampling noise.

The proposed model improves results on both synthetic and real-world datasets.

Abstract

Oversampling is a common characteristic of data representing dynamic networks. It introduces noise into representations of dynamic networks, but there has been little work so far to compensate for it. Oversampling can affect the quality of many important algorithmic problems on dynamic networks, including link prediction. Link prediction seeks to predict edges that will be added to the network given previous snapshots. We show that not only does oversampling affect the quality of link prediction, but that we can use link prediction to recover from the effects of oversampling. We also introduce a novel generative model of noise in dynamic networks that represents oversampling. We demonstrate the results of our approach on both synthetic and real-world data.