Dynamic Behavioral Mixed-Membership Model for Large Evolving Networks

TL;DR

This paper introduces a scalable, flexible, and interpretable dynamic mixed-membership model for analyzing large evolving networks, capturing node roles and their evolution over time.

Contribution

The paper presents a novel dynamic behavioral mixed-membership model (DBMM) that is scalable, parameter-free, and interpretable for large dynamic networks.

Findings

Model effectively captures evolving node roles.

Applicable to very large networks.

Uncovers meaningful dynamic patterns.

Abstract

The majority of real-world networks are dynamic and extremely large (e.g., Internet Traffic, Twitter, Facebook, ...). To understand the structural behavior of nodes in these large dynamic networks, it may be necessary to model the dynamics of behavioral roles representing the main connectivity patterns over time. In this paper, we propose a dynamic behavioral mixed-membership model (DBMM) that captures the roles of nodes in the graph and how they evolve over time. Unlike other node-centric models, our model is scalable for analyzing large dynamic networks. In addition, DBMM is flexible, parameter-free, has no functional form or parameterization, and is interpretable (identifies explainable patterns). The performance results indicate our approach can be applied to very large networks while the experimental results show that our model uncovers interesting patterns underlying the dynamics of these networks.