Detecting Time-dependent Structure in Network Data via a New Class of Latent Process Models

Abstract

We introduce a new class of latent process models for dynamic relational network data with the goal of detecting time-dependent structure. Network data are often observed over time, and static network models for such data may fail to capture relevant dynamic features. We present a new technique for identifying the emergence or disappearance of distinct subpopulations of vertices. In this formulation, a network is observed over time, with attributed edges appearing at random times. At unknown time points, subgroups of vertices may exhibit a change in behavior. Such changes may take the form of a change in the overall probability of connection within or between subgroups, or a change in the distribution of edge attributes. A mixture distribution for latent vertex positions is used to detect heterogeneities in connectivity behavior over time and over vertices. The probability of edges with various attributes at a given time is modeled using a latent-space stochastic process associated with each vertex. A random dot product model is used to describe the dependency structure of the graph. As an application we analyze the Enron email corpus.