Changepoint Detection in Highly-Atributed Dynamic Graphs

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. To address this issue, we present a strategy for monitoring anomalous behaviour in such networks. Specifically, we track the community structure within the network through the network's modularity. 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. Additionally, 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. (We will release our code upon acceptance)