Corpus ID: 1514032

Information-theoretic thresholds for community detection in sparse networks

  title={Information-theoretic thresholds for community detection in sparse networks},
  author={J. Banks and C. Moore and Joe Neeman and Praneeth Netrapalli},
  • J. Banks, C. Moore, +1 author Praneeth Netrapalli
  • Published 2016
  • Mathematics, Computer Science, Physics
  • ArXiv
  • We give upper and lower bounds on the information-theoretic threshold for community detection in the stochastic block model. Specifically, consider the symmetric stochastic block model with $q$ groups, average degree $d$, and connection probabilities $c_\text{in}/n$ and $c_\text{out}/n$ for within-group and between-group edges respectively; let $\lambda = (c_\text{in}-c_\text{out})/(qd)$. We show that, when $q$ is large, and $\lambda = O(1/q)$, the critical value of $d$ at which community… CONTINUE READING
    89 Citations

    Tables and Topics from this paper

    Detecting communities is Hard (And Counting Them is Even Harder)
    • 8
    • PDF
    On the Log Partition Function of Ising Model on Stochastic Block Model
    • 2
    • PDF
    When is Nontrivial Estimation Possible for Graphons and Stochastic Block Models?
    • 3
    • PDF
    Modularity of Erd\H{o}s-R\'enyi random graphs
    • PDF
    Contiguity and non-reconstruction results for planted partition models: the dense case
    • 20
    • PDF
    Subexponential-Time Algorithms for Sparse PCA
    • 15
    • PDF


    Community Detection in General Stochastic Block models: Fundamental Limits and Efficient Algorithms for Recovery
    • E. Abbe, Colin Sandon
    • Mathematics, Computer Science
    • 2015 IEEE 56th Annual Symposium on Foundations of Computer Science
    • 2015
    • 223
    Global and Local Information in Clustering Labeled Block Models
    • 24
    • PDF
    Crossing the KS threshold in the stochastic block model with information theory
    • E. Abbe, Colin Sandon
    • Mathematics, Computer Science
    • 2016 IEEE International Symposium on Information Theory (ISIT)
    • 2016
    • 13
    • Highly Influential
    Non-Reconstructability in the Stochastic Block Model
    • 26
    • PDF
    Spectral redemption in clustering sparse networks
    • 465
    • PDF
    Community detection in networks with unequal groups
    • 38
    • PDF
    Chasing the k-colorability threshold
    • 32
    • PDF
    Scalable detection of statistically significant communities and hierarchies, using message passing for modularity
    • P. Zhang, C. Moore
    • Mathematics, Physics
    • Proceedings of the National Academy of Sciences
    • 2014
    • 107
    • PDF