Networks with Correlated Edge Processes

TL;DR

This paper introduces methods for modeling nonstationary temporal graph processes with correlated edge variables, combining time series and static network models to analyze evolving interaction data.

Contribution

It presents novel modeling and statistical fitting techniques for nonstationary, correlated temporal graph data, addressing high-dimensional challenges.

Findings

Effective modeling of hospital contact network data.

Demonstrates high-dimensional correlation inference.

Shows the power of the proposed fitting method.

Abstract

This article proposes methods to model nonstationary temporal graph processes. This corresponds to modelling the observation of edge variables (relationships between objects) indicating interactions between pairs of nodes (or objects) exhibiting dependence (correlation) and evolution in time over interactions. This article thus blends (integer) time series models with flexible static network models to produce models of temporal graph data, and statistical fitting procedures for time-varying interaction data. We illustrate the power of our proposed fitting method by analysing a hospital contact network, and this shows the high dimensional data challenge of modelling and inferring correlation between a large number of variables.