Fast Community Detection in Dynamic and Heterogeneous Networks

TL;DR

This paper introduces DHNet, a fast, non-parametric community detection method for dynamic heterogeneous networks that accurately estimates communities without prior knowledge of their number, demonstrating superior performance in real-world data.

Contribution

The paper presents DHNet, a novel statistical framework and algorithm for community detection in dynamic heterogeneous networks, handling different node and edge types without needing the number of communities beforehand.

Findings

DHNet accurately detects communities in simulated data.

DHNet outperforms existing methods in Yelp review data.

The method is computationally efficient and interpretable.

Abstract

Dynamic heterogeneous networks describe the temporal evolution of interactions among nodes and edges of different types. While there is a rich literature on finding communities in dynamic networks, the application of these methods to dynamic heterogeneous networks can be inappropriate, due to the involvement of different types of nodes and edges and the need to treat them differently. In this paper, we propose a statistical framework for detecting common communities in dynamic and heterogeneous networks. Under this framework, we develop a fast community detection method called DHNet that can efficiently estimate the community label as well as the number of communities. An attractive feature of DHNet is that it does not require the number of communities to be known a priori, a common assumption in community detection methods. While DHNet does not require any parametric assumptions on the underlying network model, we show that the identified label is consistent under a time-varying heterogeneous stochastic block model with a temporal correlation structure and edge sparsity. We further illustrate the utility of DHNet through simulations and an application to review data from Yelp, where DHNet shows improvements both in terms of accuracy and interpretability over existing solutions.