Exact integrated completed likelihood maximisation in a stochastic block transition model for dynamic networks

The latent stochastic block model is a flexible statistical model which is widely used for the analysis of network data. Extensions of this model to a dynamic context often fail to capture the persistence of edges in contiguous network snapshots. The recently introduced stochastic block transition model addresses precisely this issue, by modelling the probabilities of creating a new edge and of maintaining an edge over time. Using a model-based clustering approach, this paper illustrates a methodology to fit stochastic block transition models under a Bayesian framework. The method relies on a greedy optimisation procedure to maximise the exact integrated completed likelihood. The computational efficiency of the algorithm used makes the methodology scalable and appropriate for the analysis of large network datasets. Crucially, the optimal number of latent groups is automatically selected at no additional computing cost. The efficacy of the method is demonstrated through applications to both artificial and real datasets.

• Publication year

  2017

• Venue

  arXiv: Methodology

• Publication date

  2017-10-10

• Fields of study

  Mathematics, Computer Science

• Identifiers
  arXiv 1710.03551
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Dealing with reciprocity in dynamic stochastic block models

  2018cited by this paper
• Multiple change points detection and clustering in dynamic networks

  2017cited by this paper
• Choosing the number of groups in a latent stochastic blockmodel for dynamic networks

  2017cited by this paper
• Random graph models for dynamic networks

  2016influential reference
• Interlocking directorates in Irish companies using a latent space model for bipartite networks

  2016cited by this paper
• Statistical clustering of temporal networks through a dynamic stochastic block model

  2015influential reference
• Latent Space Models for Dynamic Networks

  2015cited by this paper
• Model selection and clustering in stochastic block models based on the exact integrated complete data likelihood

  2015influential reference
• A semiparametric extension of the stochastic block model for longitudinal networks

  2015cited by this paper
• R: A language and environment for statistical computing.

  2014cited by this paper
• Inferring structure in bipartite networks using the latent blockmodel and exact ICL

  2014cited by this paper
• Dynamic Stochastic Blockmodels for Time-Evolving Social Networks

  2014cited by this paper
• Stochastic Block Transition Models for Dynamic Networks

  2014influential reference
• Bayesian variable selection for latent class analysis using a collapsed Gibbs sampler

  2014cited by this paper
• Choosing the number of clusters in a finite mixture model using an exact integrated completed likelihood criterion

  2014influential reference
• Modeling heterogeneity in random graphs through latent space models: a selective review

  2014cited by this paper
• Dynamic Probabilistic Models for Latent Feature Propagation in Social Networks

  2013cited by this paper
• Asymptotic behaviour of the posterior distribution in overfitted mixture models

  2011cited by this paper
• Detecting communities and their evolutions in dynamic social networks—a Bayesian approach

  2011cited by this paper
• Block clustering with collapsed latent block models

  2010cited by this paper
• Stochastic blockmodels and community structure in networks

  2010cited by this paper
• Dynamic Infinite Relational Model for Time-varying Relational Data Analysis

  2010cited by this paper
• Variational Bayesian inference and complexity control for stochastic block models

  2009cited by this paper
• Community detection in graphs

  2009cited by this paper
• A mixture model for random graphs

  2008cited by this paper
• Bayesian finite mixtures with an unknown number of components: The allocation sampler

  2007cited by this paper
• Reality mining: sensing complex social systems

  2006cited by this paper
• Latent Space Approaches to Social Network Analysis

  2002cited by this paper
• Cluster Ensembles --- A Knowledge Reuse Framework for Combining Multiple Partitions

  2002cited by this paper
• Estimation and Prediction for Stochastic Blockstructures

  2001cited by this paper
• Assessing a Mixture Model for Clustering with the Integrated Completed Likelihood

  2000influential reference
• Stochastic Blockmodels for Directed Graphs

  1987cited by this paper
• Stochastic blockmodels: First steps

  1983cited by this paper
• Computational Statistics and Data Analysis

  year unknowncited by this paper

• Continuous latent position models for instantaneous interactions

  2021cites this paper
• An exact algorithm for time-dependent variational inference for the dynamic stochastic block model

  2020cites this paper
• A stochastic block model for interaction lengths

  2020cites this paper
• Limits of Model Selection, Link Prediction, and Community Detection

  2019cites this paper
• A dynamic stochastic blockmodel for interaction lengths

  2019cites this paper
• Block-Structure Based Time-Series Models For Graph Sequences

  2018influential citation
• The Block Point Process Model for Continuous-time Event-based Dynamic Networks

  2017cites this paper