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

TL;DR

This paper introduces the Multiplicative Attribute Graph (MAG) model, which effectively captures the structure of social networks with node attributes by modeling edge probabilities as products of attribute affinities, and provides a scalable estimation method.

Contribution

The paper proposes a novel MAG model for networks with node attributes and develops a scalable variational EM algorithm for parameter estimation.

Findings

MAG accurately models network connectivity patterns.

The model offers insights into attribute influence on network structure.

Scalable estimation method demonstrated on real networks.

Abstract

Networks arising from social, technological and natural domains exhibit rich connectivity patterns and nodes in such networks are often labeled with attributes or features. We address the question of modeling the structure of networks where nodes have attribute information. We present a Multiplicative Attribute 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 provides insights into how different attributes shape the network structure.