Learn R Programming

noisySBM (version 0.1.4)

Noisy Stochastic Block Mode: Graph Inference by Multiple Testing

Description

Variational Expectation-Maximization algorithm to fit the noisy stochastic block model to an observed dense graph and to perform a node clustering. Moreover, a graph inference procedure to recover the underlying binary graph. This procedure comes with a control of the false discovery rate. The method is described in the article "Powerful graph inference with false discovery rate control" by T. Rebafka, E. Roquain, F. Villers (2020) .

Copy Link

Version

Install

install.packages('noisySBM')

Monthly Downloads

230

Version

0.1.4

License

GPL-2

Maintainer

Tabea Rebafka

Last Published

December 16th, 2020

Functions in noisySBM (0.1.4)

Evalute the adjusted Rand index

convert a clustering into a 0-1-matrix

split group q of provided tau randomly into two into

computation of the Integrated Classification Likelihood criterion

evaluation of the objective in the Gauss model

convertGroupPairIdentifier

takes a scalar indice of a group pair (q,l) and returns the values q and l

convertGroupPair

transform a pair of block identifiers (q,l) into an identifying integer

evaluate the objective in the Gamma model

optimal number of SBM blocks

new graph inference procedure

Evaluate tau_q*tau_l in the noisy stochastic block model

plot the data matrix, the inferred graph and/or the true binary graph

main function of VEM algorithm for fixed number of latent blocks in parallel computing

auxiliary function for the computation of q-values

evaluate the density in the current model

compute q-values in the noisy stochastic block model

initialPointsByMerge

Construct initial values with Q groups by meging groups of a solution obtained with Q+1 groups

compute a list of initial points for the VEM algorithm

convertNodePair

transform a pair of nodes (i,j) into an identifying integer

compute conditional l-values in the noisy stochastic block model

main function of VEM algorithm with fixed number of SBM blocks

corrects values of the variational parameters tau that are too close to the 0 or 1

compute rho associated with given values of w, nu0 and nu

VEM algorithm to adjust the noisy stochastic block model to an observed dense adjacency matrix

compute the MLE in the Gamma model using the Newton-Raphson method

Create new values of tau by splitting groups of provided tau

compute intial values for tau

compute initial values of rho

Output of fitNSBM() on a dataset applied in the exponential NSBM

initialPointsBySplit

Construct initial values with Q groups by splitting groups of a solution obtained with Q-1 groups

returns a list of all possible node pairs (i,j)

spectralClustering

spectral clustering with absolute values

Output of fitNSBM() on a dataset applied in the Gamma NSBM

Compute one iteration to solve the fixed point equation in the VE-step

update_newton_gamma

Perform one iteration of the Newton-Raphson to compute the MLE of the parameters of the Gamma distribution

simulation of a graph according the noisy stochastic block model

Output of fitNSBM() on a dataset applied in the Gaussian NSBM

Create new initial values by merging pairs of groups of provided tau