The method of moments and degree distributions for network models

TL;DR

This paper introduces a general method of moments approach for fitting probability models on graphs using empirical pattern counts, with proven consistency and asymptotic properties, especially focusing on degree distributions.

Contribution

It develops a versatile method of moments framework for graph models, establishing theoretical guarantees and extending to degree distribution analysis.

Findings

Proves consistency of the method as graph size increases.

Establishes asymptotic properties of empirical graph moments.

Applies to models with various average degrees, including constant.

Abstract

Probability models on graphs are becoming increasingly important in many applications, but statistical tools for fitting such models are not yet well developed. Here we propose a general method of moments approach that can be used to fit a large class of probability models through empirical counts of certain patterns in a graph. We establish some general asymptotic properties of empirical graph moments and prove consistency of the estimates as the graph size grows for all ranges of the average degree including $\Omega(1)$. Additional results are obtained for the important special case of degree distributions.