An improved spectral clustering method for mixed membership community detection

TL;DR

This paper introduces Mixed-ISC, an improved spectral clustering algorithm for mixed membership community detection that is efficient, consistent, and performs well on both simulated and real networks, especially in weak signal scenarios.

Contribution

The paper proposes a novel spectral algorithm, Mixed-ISC, that uses multiple eigenvectors for better mixed membership community detection under the DCMM model, with proven asymptotic consistency.

Findings

Mixed-ISC outperforms benchmark methods in experiments.

The algorithm is effective on weak signal networks.

Numerical results confirm the theoretical consistency.

Abstract

Community detection has been well studied recent years, but the more realistic case of mixed membership community detection remains a challenge. Here, we develop an efficient spectral algorithm Mixed-ISC based on applying more than K eigenvectors for clustering given K communities for estimating the community memberships under the degree-corrected mixed membership (DCMM) model. We show that the algorithm is asymptotically consistent. Numerical experiments on both simulated networks and many empirical networks demonstrate that Mixed-ISC performs well compared to a number of benchmark methods for mixed membership community detection. Especially, Mixed-ISC provides satisfactory performances on weak signal networks.