fitSBMcollection function

Fit a unique stochastic block model to a collection of networks

fitSBMcollection() is a subversion of graphClustering() where no stopping criterion is applied. So all networks are ultimately merged to a single cluster and considered as i.i.d realisations of a single stochastic block model.

fitSBMcollection(
  allAdj,
  hyperParam = list(alpha = 0.5, eta = 0.5, zeta = 0.5, lambda = 0.5),
  nbCores = 1
)

Arguments

• allAdj: list of adjacency matrices
• hyperParam: hyperparameters of prior distributions
• nbCores: number of cores for parallelization

Returns

list with the following fields: $nodeClusterings is a list with the node labels for each networks,$theta contains the estimated SBM parameter, $ICL is the value of the ICL criterion of the final clustering

Examples

theta <- list(pi=c(.5,.5), gamma=matrix((1:4)/8,2,2))
obs <- rCollectSBM(rep(10,4), theta)$listGraphs
res <- fitSBMcollection(obs, nbCores=1)