3 Hits in 2.4 sec

missSBM: An R Package for Handling Missing Values in the Stochastic Block Model [article]

Pierre Barbillon, Julien Chiquet, Timothée Tabouy
2021 arXiv   pre-print
The Stochastic Block Model (SBM) is a popular probabilistic model for random graphs.  ...  This paper introduces missSBM, an R-package fitting the SBM when the network is partially observed, i.e., the adjacency matrix contains not only 1's or 0's encoding presence or absence of edges but also  ...  Acknowledgments The authors thank all members of MIRES group for fruitful discussions on network sampling designs.  ... 
arXiv:1906.12201v3 fatcat:qx4ax7vg6reljkftjnepklng64

Variational Inference for Stochastic Block Models from Sampled Data [article]

Timothée Tabouy, Pierre Barbillon, Julien Chiquet
2019 arXiv   pre-print
This paper deals with non-observed dyads during the sampling of a network and consecutive issues in the inference of the Stochastic Block Model (SBM).  ...  We introduce variants of the variational EM algorithm for inferring the SBM under various sampling designs (MAR and NMAR) all available as an R package.  ...  In particular, we thank Vanesse Labeyrie (CIRAD-Green) for sharing the seed exchange data and for related discussions on the analysis.  ... 
arXiv:1707.04141v6 fatcat:px5a3mel5jfcva5kniwnazf4iq

Maximum Likelihood Estimation of Sparse Networks with Missing Observations [article]

Solenne Gaucher, Olga Klopp
2021 arXiv   pre-print
In this work, we consider networks generated under the sparse graphon model and the in-homogeneous random graph model with missing observations.  ...  Using the Stochastic Block Model as a parametric proxy, we bound the risk of the maximum likelihood estimator of network connections probabilities , and show that it is minimax optimal.  ...  The authors want to thank Catherine Matias and Nicolas Verzelen for extremely valuable suggestions and discussions. The authors declare that there is no conflict of interest.  ... 
arXiv:1902.10605v2 fatcat:ippvrbijafg4paqi33t5ry2nfy