UBSea: A Unified Community Detection Framework

TL;DR

UBSea is a novel community detection framework that unifies multiple mixing patterns in networks, automatically identifies the pattern type, and demonstrates superior performance on simulated and real-world data.

Contribution

The paper introduces UBSea, a unified framework that extends modularity to detect all community mixing types and automatically determines the mixing pattern.

Findings

Effective in detecting assortative, disassortative, and core-periphery structures.

Shows consistent community estimation under stochastic block models.

Performs well on both simulated and real-world networks.

Abstract

Detecting communities in networks and graphs is an important task across many disciplines such as statistics, social science and engineering. There are generally three different kinds of mixing patterns for the case of two communities: assortative mixing, disassortative mixing and core-periphery structure. Modularity optimization is a classical way for fitting network models with communities. However, it can only deal with assortative mixing and disassortative mixing when the mixing pattern is known and fails to discover the core-periphery structure. In this paper, we extend modularity in a strategic way and propose a new framework based on Unified Bigroups Standadized Edge-count Analysis (UBSea). It can address all the formerly mentioned community mixing structures. In addition, this new framework is able to automatically choose the mixing type to fit the networks. Simulation studies show that the new framework has superb performance in a wide range of settings under the stochastic block model and the degree-corrected stochastic block model. We show that the new approach produces consistent estimate of the communities under a suitable signal-to-noise-ratio condition, for the case of a block model with two communities, for both undirected and directed networks. The new method is illustrated through applications to several real-world datasets.