A useful criterion on studying consistent estimation in community detection

TL;DR

This paper introduces a unified criterion called SCSTC for analyzing consistent community detection in networks, revealing new insights into the limitations and optimal conditions of spectral methods, including the re-evaluation of the SPACL algorithm.

Contribution

It proposes the SCSTC criterion for comparing community detection methods, re-establishes convergence rates for the SPACL algorithm, and extends results to degree-corrected models, improving understanding of estimation consistency.

Findings

Identifies inconsistencies in separation condition and sharp threshold.

Re-establishes convergence rates for the SPACL algorithm.

Shows improved error bounds and weaker sparsity requirements.

Abstract

In network analysis, developing a unified theoretical framework that can compare methods under different models is an interesting problem. This paper proposes a partial solution to this problem. We summarize the idea of using separation condition for a standard network and sharp threshold of Erd\"os-R\'enyi random graph to study consistent estimation, compare theoretical error rates and requirements on network sparsity of spectral methods under models that can degenerate to stochastic block model as a four-step criterion SCSTC. Using SCSTC, we find some inconsistent phenomena on separation condition and sharp threshold in community detection. Especially, we find original theoretical results of the SPACL algorithm introduced to estimate network memberships under the mixed membership stochastic blockmodel were sub-optimal. To find the formation mechanism of inconsistencies, we re-establish theoretical convergence rates of this algorithm by applying recent techniques on row-wise eigenvector deviation. The results are further extended to the degree corrected mixed membership model. By comparison, our results enjoy smaller error rates, lesser dependence on the number of communities, weaker requirements on network sparsity, and so forth. Furthermore, separation condition and sharp threshold obtained from our theoretical results match classical results, which shows the usefulness of this criterion on studying consistent estimation.