Annals of Applied Statistics
- Ann. Appl. Stat.
- Volume 4, Number 2 (2010), 715-742.
Uncovering latent structure in valued graphs: A variational approach
As more and more network-structured data sets are available, the statistical analysis of valued graphs has become common place. Looking for a latent structure is one of the many strategies used to better understand the behavior of a network. Several methods already exist for the binary case.
We present a model-based strategy to uncover groups of nodes in valued graphs. This framework can be used for a wide span of parametric random graphs models and allows to include covariates. Variational tools allow us to achieve approximate maximum likelihood estimation of the parameters of these models. We provide a simulation study showing that our estimation method performs well over a broad range of situations. We apply this method to analyze host–parasite interaction networks in forest ecosystems.
Ann. Appl. Stat., Volume 4, Number 2 (2010), 715-742.
First available in Project Euclid: 3 August 2010
Permanent link to this document
Digital Object Identifier
Mathematical Reviews number (MathSciNet)
Zentralblatt MATH identifier
Mariadassou, Mahendra; Robin, Stéphane; Vacher, Corinne. Uncovering latent structure in valued graphs: A variational approach. Ann. Appl. Stat. 4 (2010), no. 2, 715--742. doi:10.1214/10-AOAS361. https://projecteuclid.org/euclid.aoas/1280842137
- Supplementary material: Interaction network between tree and fungal species. This file contains: •The adjacency matrix of interactions between tree and fungal species. •The list of the tree species. •The list of the fungal species. •The matrix of genetic distances between tree species. •The matrix of geographical distances between tree species. •The matrix of taxonomic distances between fungal species. •The matrix of nutritional type of the fungal species.