Modeling Social Networks with Node Attributes using the Multiplicative Attribute Graph Model

摘要

Networks arising from social, technological and natural domains exhibit rich connectiv ity patterns and nodes in such networks are often labeled with attributes or features. We address the question of modeling the struc ture of networks where nodes have attribute information. We present a Multiplicative At tribute Graph (MAG) model that considers nodes with categorical attributes and models the probability of an edge as the product of individual attribute link formation affinities. We develop a scalable variational expectation maximization parameter estimation method. Experiments show that MAG model reliably captures network connectivity as well as pro vides insights into how different attributes shape the network structure.