The inference use a greedy algorithm to navigate between model size. For a given model size, the inference is done via a variational EM algorithm. The returned model is the one with the highest ICL criterion among all visited models.

By default the algorithm fits a single level SBM for each level, before inferring the multilevel network. This step can be skipped by specifying an initial clustering with the init_clustering. Also, a given model size can be force by setting the parameters nb_clusters to a given value.

mlvsbm_estimate_network(
  mlv,
  nb_clusters = NULL,
  init_clustering = NULL,
  nb_cores = NULL,
  init_method = "hierarchical"
)

Arguments

mlv

A MLVSBM object, the network to be inferred.

nb_clusters

A list of 2 integers, the model size. If left to NULL, the algorithm will navigate freely. Otherwise it will navigate between the specified model size and its neighbors.

init_clustering

A list of 2 vectors of integers of the same length as the number of node of each level. If specified, the algorithm will start from this clustering, then navigate freely.

nb_cores

An integer, the number of cores to use. Default to 1 for Windows and detectCores()/2 for Linux and MacOS

init_method

One of "hierarchical" (the default) or "spectral", "spectral" might be more efficient but can lead to some numeric errors. Not used when int_clustering is given.

Value

A FitMLVSBM object, the best inference of the network

Examples

my_mlvsbm <- MLVSBM::mlvsbm_simulate_network(
  n = list(I = 10, O = 20), # Number of nodes for the lower level and the upper level
  Q = list(I = 2, O = 2), # Number of blocks for the lower level and the upper level
  pi = c(.3, .7), # Block proportion for the upper level, must sum to one
  gamma = matrix(c(.9, .2,   # Block proportion for the lower level,
                   .1, .8), # each column must sum to one
                 nrow = 2, ncol = 2, byrow = TRUE),
  alpha = list(I = matrix(c(.8, .2,
                            .2, .1),
                          nrow = 2, ncol = 2, byrow = TRUE), # Connection matrix
               O = matrix(c(.99, .3,
                            .3, .1),
                          nrow = 2, ncol = 2, byrow = TRUE)),# between blocks
  directed = list(I = FALSE, O = FALSE), # Are the upper and lower level directed or not ?
  affiliation = "preferential") # How the affiliation matrix is generated
fit <- MLVSBM::mlvsbm_estimate_network(mlv = my_mlvsbm, nb_cores = 1)
#> 

#> 





[1] "Infering lower level :"
#> [1] "# blocks: 1, ICL = -30.5464688181517 !"
#> 

#> 






[1] "Infering upper level :"
#> [1] "# blocks: 1, ICL = -94.8607031904538 !"
#> [1] "======= # Individual clusters : 1 , # Organisation clusters 1,  ICL : -125.407172008605========"
#> [1] "======= # Individual blocks : 1 , # Organizational blocks 2,  ICL : -124.4436233372========"
#> [1] "======= # Individual blocks : 2 , # Organizational blocks 2,  ICL : -121.813050465274========"
#> [1] "======= # Individual blocks : 2 , # Organizational blocks 2,  ICL : -121.813050465274========"
#> [1] "ICL for independent levels : -125.407172008605"
#> [1] "ICL for interdependent levels : -121.813050465274"
#> [1] "=====Interdependence is detected between the two levels!====="