Asymptotic distribution of modularity in networks
Consider a simple, undirected graph with \(n\) vertices, \(m\) edges and adjacency matrix \(\mathbf{A}=(A_{ij})_{n\times n}\). Let vertex \(i\) have degree \(k_i\). Suppose that the vertices of the graph are divided into \(K\) groups. The modularity of this partition is \[ \frac{1}{2m}\sum_{i,j}\left(A_{ij}-\frac{k_ik_j}{2m}\right)\delta_{i,j}\,, \] where \(\delta_{i,j}\) is 1 if vertices \(i\) and \(j\) are in the same group, and 0 otherwise. The modularity is one measure of the extent to which vertices in the same group are connected to each other. Suppose that the proportion of vertices in each group is fixed. The authors establish the asymptotic (as \(n\rightarrow\infty\)) normal distribution of the modularity, with explicit mean and variance, under the free labeling, where vertices are assigned to groups via a multinomial distribution with parameters given by the proportion of vertices in each group. This asymptotic normality holds under relatively mild growth conditions on the vertex degrees, which ensure that the variance is not degenerate in the limit. Applications of this result to assessing statistical significance of network partitions are discussed, and numerical examples illustrate both the quality of the normal approximation and applications to real data.
- The asymptotic distribution of modularity in weighted signed networks
- A nonparametric view of network models and Newman–Girvan and other modularities
- Network modularity in the presence of covariates
- A Hypothesis Testing Framework for Modularity Based Network Community Detection
- When are networks truly modular?
- A Hypothesis Testing Framework for Modularity Based Network Community Detection
- Detecting network communities: a new systematic and efficient algorithm
- scientific article; zbMATH DE number 3965276 (Why is no real title available?)
- scientific article; zbMATH DE number 3723610 (Why is no real title available?)
- Networks. An introduction.
- NOTES ON CONTINUOUS STOCHASTIC PHENOMENA
- Social and economic networks.
- Statistical mechanics of complex networks
- The maximum degree of a random graph
- The Structure and Function of Complex Networks
- Degree distribution and assortativity in line graphs of complex networks
- Validation of community robustness
- Modulus metrics on networks
- Modularity of complex networks models
- On community structure validation in real networks
- Dynamics on modular networks with heterogeneous correlations
- A nonparametric view of network models and Newman–Girvan and other modularities
- Asymptotic distributions in random graphs with applications to social networks
- Network modularity in the presence of covariates
- The asymptotic distribution of modularity in weighted signed networks
- Moderate deviation principle of modularity in network
- On Inference for Modularity Statistics in Structured Networks
- Fast and accurate determination of modularity and its effect size
- When are networks truly modular?
This page was built for publication: Asymptotic distribution of modularity in networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2174525)
