ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 1510.05956
187
78
v1v2v3v4v5v6 (latest)

Optimal Cluster Recovery in the Labeled Stochastic Block Model

20 October 2015
Seyoung Yun
Alexandre Proutiere
ArXiv (abs)PDFHTML
Abstract

We consider the problem of community detection or clustering in the labeled Stochastic Block Model (LSBM) with a finite number KKK of clusters of sizes linearly growing with the global population of items nnn. Every pair of items is labeled independently at random, and label ℓ\ellℓ appears with probability p(i,j,ℓ)p(i,j,\ell)p(i,j,ℓ) between two items in clusters indexed by iii and jjj, respectively. The objective is to reconstruct the clusters from the observation of these random labels. Clustering under the SBM and their extensions has attracted much attention recently. Most existing work aimed at characterizing the set of parameters such that it is possible to infer clusters either positively correlated with the true clusters, or with a vanishing proportion of misclassified items, or exactly matching the true clusters. We find the set of parameters such that there exists a clustering algorithm with at most sss misclassified items in average under the general LSBM and for any s=o(n)s=o(n)s=o(n), which solves one open problem raised in \cite{abbe2015community}. We further develop an algorithm, based on simple spectral methods, that achieves this fundamental performance limit within O(n\mboxpolylog(n))O(n \mbox{polylog}(n))O(n\mboxpolylog(n)) computations and without the a-priori knowledge of the model parameters.

View on arXiv
Comments on this paper