Bayesian community detection.

    Research output: Contribution to journalJournal articleResearchpeer-review

    1417 Downloads (Pure)

    Abstract

    Many networks of scientific interest naturally decompose into clusters or communities with comparatively fewer external than internal links; however, current Bayesian models of network communities do not exert this intuitive notion of communities. We formulate a nonparametric Bayesian model for community detection consistent with an intuitive definition of communities and present a Markov chain Monte Carlo procedure for inferring the community structure. A Matlab toolbox with the proposed inference procedure is available for download. On synthetic and real networks, our model detects communities consistent with ground truth, and on real networks, it outperforms existing approaches in predicting missing links. This suggests that community structure is an important structural property of networks that should be explicitly modeled.
    Original languageEnglish
    JournalNeural Computation
    Volume24
    Issue number9
    Pages (from-to)2434-2456
    ISSN0899-7667
    DOIs
    Publication statusPublished - 2012

    Keywords

    • Community detection
    • Complex networks
    • Infinite relational Model
    • Stochastic Block-model
    • Modularity
    • Normalized Cut

    Cite this

    @article{7f39116baeb9487ab6f013f50e0c7e85,
    title = "Bayesian community detection.",
    abstract = "Many networks of scientific interest naturally decompose into clusters or communities with comparatively fewer external than internal links; however, current Bayesian models of network communities do not exert this intuitive notion of communities. We formulate a nonparametric Bayesian model for community detection consistent with an intuitive definition of communities and present a Markov chain Monte Carlo procedure for inferring the community structure. A Matlab toolbox with the proposed inference procedure is available for download. On synthetic and real networks, our model detects communities consistent with ground truth, and on real networks, it outperforms existing approaches in predicting missing links. This suggests that community structure is an important structural property of networks that should be explicitly modeled.",
    keywords = "Community detection, Complex networks, Infinite relational Model, Stochastic Block-model, Modularity, Normalized Cut",
    author = "Morten M{\o}rup and Schmidt, {Mikkel N}",
    year = "2012",
    doi = "10.1162/NECO_a_00314",
    language = "English",
    volume = "24",
    pages = "2434--2456",
    journal = "Neural Computation",
    issn = "0899-7667",
    publisher = "M I T Press",
    number = "9",

    }

    Bayesian community detection. / Mørup, Morten; Schmidt, Mikkel N.

    In: Neural Computation, Vol. 24, No. 9, 2012, p. 2434-2456.

    Research output: Contribution to journalJournal articleResearchpeer-review

    TY - JOUR

    T1 - Bayesian community detection.

    AU - Mørup, Morten

    AU - Schmidt, Mikkel N

    PY - 2012

    Y1 - 2012

    N2 - Many networks of scientific interest naturally decompose into clusters or communities with comparatively fewer external than internal links; however, current Bayesian models of network communities do not exert this intuitive notion of communities. We formulate a nonparametric Bayesian model for community detection consistent with an intuitive definition of communities and present a Markov chain Monte Carlo procedure for inferring the community structure. A Matlab toolbox with the proposed inference procedure is available for download. On synthetic and real networks, our model detects communities consistent with ground truth, and on real networks, it outperforms existing approaches in predicting missing links. This suggests that community structure is an important structural property of networks that should be explicitly modeled.

    AB - Many networks of scientific interest naturally decompose into clusters or communities with comparatively fewer external than internal links; however, current Bayesian models of network communities do not exert this intuitive notion of communities. We formulate a nonparametric Bayesian model for community detection consistent with an intuitive definition of communities and present a Markov chain Monte Carlo procedure for inferring the community structure. A Matlab toolbox with the proposed inference procedure is available for download. On synthetic and real networks, our model detects communities consistent with ground truth, and on real networks, it outperforms existing approaches in predicting missing links. This suggests that community structure is an important structural property of networks that should be explicitly modeled.

    KW - Community detection

    KW - Complex networks

    KW - Infinite relational Model

    KW - Stochastic Block-model

    KW - Modularity

    KW - Normalized Cut

    U2 - 10.1162/NECO_a_00314

    DO - 10.1162/NECO_a_00314

    M3 - Journal article

    VL - 24

    SP - 2434

    EP - 2456

    JO - Neural Computation

    JF - Neural Computation

    SN - 0899-7667

    IS - 9

    ER -