Moments of Uniform Random Multigraphs with Fixed Degree Sequences

TL;DR

This paper introduces a new estimator for the expected adjacency matrix of random multigraphs with fixed degree sequences, improving accuracy over standard approximations especially for non-sparse or non-simple graphs, with applications in network analysis.

Contribution

The authors develop a novel estimator derived from Markov Chain Monte Carlo stationarity conditions, providing error bounds and demonstrating superior accuracy over traditional methods.

Findings

The new estimator reduces relative error by an order of magnitude compared to standard approximation.

It significantly impacts modularity maximization results depending on the estimator used.

The approach is validated on synthetic and real-world degree sequences.

Abstract

We study the expected adjacency matrix of a uniformly random multigraph with fixed degree sequence $\mathbf{d} \in \mathbb{Z}_+^n$. This matrix arises in a variety of analyses of networked data sets, including modularity-maximization and mean-field theories of spreading processes. Its structure is well-understood for large, sparse, simple graphs: the expected number of edges between nodes $i$ and $j$ is roughly $\frac{d_id_j}{\sum_\ell{d_\ell}}$. Many network data sets are neither large, sparse, nor simple, and in these cases the standard approximation no longer applies. We derive a novel estimator using a dynamical approach: the estimator emerges from the stationarity conditions of a class of Markov Chain Monte Carlo algorithms for graph sampling. We derive error bounds for this estimator, and provide an efficient scheme with which to compute it. We test the estimator on synthetic and empirical degree sequences, finding that it enjoys relative error against ground truth a full order of magnitude smaller than the standard approximation. We then compare modularity maximization techniques using both the standard and novel estimator, finding that the qualitative structure of the optimization landscape depends significantly on the estimator choice. Our results emphasize the importance of using carefully specified random graph models in data scientific applications.