Estimating Network Models using Neural Networks

TL;DR

This paper introduces a neural network-based method for estimating exponential random graph models (ERGMs), enabling faster and more efficient network parameter estimation by learning the mapping from parameters to network statistics.

Contribution

The authors develop a neural network approach that learns the parameter-to-statistics mapping in ERGMs, allowing for rapid, parallelizable estimation and handling model misspecification.

Findings

Method performs well in illustrative examples

Enables fast, parallelizable estimation

Accommodates extra network statistics

Abstract

Exponential random graph models (ERGMs) are very flexible for modeling network formation but pose difficult estimation challenges due to their intractable normalizing constant. Existing methods, such as MCMC-MLE, rely on sequential simulation at every optimization step. We propose a neural network approach that trains on a single, large set of parameter-simulation pairs to learn the mapping from parameters to average network statistics. Once trained, this map can be inverted, yielding a fast and parallelizable estimation method. The procedure also accommodates extra network statistics to mitigate model misspecification. Some simple illustrative examples show that the method performs well in practice.