(Un)detectable cluster structure in sparse networks

dc.creatorReichardt, Joerg
dc.creatorLeone, Michele
dc.date2007-11-09
dc.date.accessioned2026-07-07T12:11:30Z
dc.date.available2026-07-07T12:11:30Z
dc.descriptionWe study the problem of recovering a known cluster structure in a sparse network, also known as the planted partitioning problem, by means of statistical mechanics. We find a sharp transition from un-recoverable to recoverable structure as a function of the separation of the clusters. For multivariate data, such transitions have been observed frequently, but always as a function of the number of data points provided, i.e. given a large enough data set, two point clouds can always be recognized as different clusters, as long as their separation is non-zero. In contrast, for the sparse networks studied here, a cluster structure remains undetectable even in an infinitely large network if a critical separation is not exceeded. We give analytic formulas for this critical separation as a function of the degree distribution of the network and calculate the shape of the recoverability-transition. Our findings have implications for unsupervised learning and data-mining in relational data bases and provide bounds on the achievable performance of graph clustering algorithms.
dc.description4 Pages, 2 Figures
dc.identifierhttps://arxiv.org/abs/0711.1452
dc.identifierhttp://arxiv.org/abs/0711.1452
dc.identifierPhys. Rev. Lett. 101, 078701 (2008)
dc.identifierdoi:10.1103/PhysRevLett.101.078701
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/210238
dc.subjectDisordered Systems and Neural Networks
dc.subjectStatistical Mechanics
dc.title(Un)detectable cluster structure in sparse networks
dc.typetext

Files

Collections