Learn R Programming

randnet (version 0.7)

Random Network Model Estimation, Selection and Parameter Tuning

Description

Model selection and parameter tuning procedures for a class of random network models. The model selection can be done by a general cross-validation framework called ECV from Li et. al. (2016) . Several other model-based and task-specific methods are also included, such as NCV from Chen and Lei (2016) , likelihood ratio method from Wang and Bickel (2015) , spectral methods from Le and Levina (2015) . Many network analysis methods are also implemented, such as the regularized spectral clustering (Amini et. al. 2013 ) and its degree corrected version and graphon neighborhood smoothing (Zhang et. al. 2015 ). It also includes the consensus clustering of Gao et. al. (2014) , the method of moments estimation of nomination SBM of Li et. al. (2020) , and the network mixing method of Li and Le (2021) . It also includes the informative core-periphery data processing method of Miao and Li (2021) . The work to build and improve this package is partially supported by the NSF grants DMS-2015298 and DMS-2015134.

Copy Link

Version

Install

install.packages('randnet')

Monthly Downloads

308

Version

0.7

License

GPL (>= 2)

Maintainer

Tianxi Li

Last Published

May 20th, 2023

Functions in randnet (0.7)

reg.SSP

detects communities by regularized spherical spectral clustering
NSBM.estimate

estimates nomination SBM parameters given community labels by the method of moments
network.mixing.Bfold

estimates network connection probability by network mixing with B-fold averaging
network.mixing

estimates network connection probability by network mixing
randnet-package

Statistical modeling of random networks with model estimation, selection and parameter tuning
reg.SP

clusters nodes by regularized spectral clustering
DCSBM.estimate

Estimates DCSBM model
smooth.oracle

oracle smooth graphon estimation
ECV.block

selecting block models by ECV
LSM.PGD

estimates inner product latent space model by projected gradient descent
ECV.Rank

estimates optimal low rank model for a network
ECV.nSmooth.lowrank

selecting tuning parameter for neighborhood smoothing estimation of graphon model
InformativeCore

identify the informative core component of a network
NSBM.Gen

Generates networks from nomination stochastic block model
SBM.estimate

estimates SBM parameters given community labels
LRBIC

selecting number of communities by asymptotic likelihood ratio
ConsensusClust

clusters nodes by concensus (majority voting) initialized by regularized spectral clustering
BHMC.estimate

Estimates the number of communities under block models by the spectral methods
BlockModel.Gen

Generates networks from degree corrected stochastic block model
RDPG.Gen

generates random networks from random dot product graph model
USVT

estimates the network probability matrix by the improved universal singular value thresholding
RightSC

clusters nodes in a directed network by regularized spectral clustering on right singular vectors
NCV.select

selecting block models by NCV
NMI

calculates normalized mutual information
nSmooth

estimates probabilty matrix by neighborhood smoothing