Changepoint Detection in Highly-Attributed Dynamic Graphs

TL;DR

This paper introduces a GNN-based method for detecting anomalies in dynamic, highly-attributed networks by tracking modularity changes, effectively identifying real-world events in complex social networks.

Contribution

It proposes a novel approach using GNNs to estimate modularity in highly-attributed dynamic graphs, enhancing anomaly detection capabilities.

Findings

Successfully detects change points in simulated networks.

Identifies real-world event in Iran Twitter reply network.

GNN-based modularity estimation improves detection accuracy.

Abstract

Detecting anomalous behavior in dynamic networks remains a constant challenge. This problem is further exacerbated when the underlying topology of these networks is affected by individual highly-dimensional node attributes. We address this issue by tracking a network's modularity as a proxy of its community structure. We leverage Graph Neural Networks (GNNs) to estimate each snapshot's modularity. GNNs can account for both network structure and high-dimensional node attributes, providing a comprehensive approach for estimating network statistics. Our method is validated through simulations that demonstrate its ability to detect changes in highly-attributed networks by analyzing shifts in modularity. Moreover, we find our method is able to detect a real-world event within the \#Iran Twitter reply network, where each node has high-dimensional textual attributes.