Skip to Main content Skip to Navigation
Conference papers

Reconstruction in the Labeled Stochastic Block Model

Abstract : The labeled stochastic block model is a random graph model representing networks with community structure and interactions of multiple types. In its simplest form, it consists of two communities of approximately equal size, and the edges are drawn and labeled at random with probability depending on whether their two endpoints belong to the same community or not. It has been conjectured in [1] that this model exhibits a phase transition: reconstruction (i.e. identification of a partition positively correlated with the "true partition" into the underlying communities) would be feasible if and only if a model parameter exceeds a threshold. We prove one half of this conjecture, i.e., reconstruction is impossible when below the threshold. In the converse direction, we introduce a suitably weighted graph. We show that when above the threshold by a specific constant, reconstruction is achieved by (1) minimum bisection, and (2) a spectral method combined with removal of nodes of high degree.
Document type :
Conference papers
Complete list of metadata
Contributor : Marc Lelarge Connect in order to contact the contributor
Submitted on : Wednesday, December 11, 2013 - 6:46:50 PM
Last modification on : Tuesday, January 11, 2022 - 11:16:25 AM


  • HAL Id : hal-00917425, version 1


Marc Lelarge, Laurent Massoulié, Jiaming Xu. Reconstruction in the Labeled Stochastic Block Model. IEEE Information Theory Workshop, Sep 2013, Seville, Spain. ⟨hal-00917425⟩



Les métriques sont temporairement indisponibles