UNCOVERING LATENT STRUCTURE IN VALUED GRAPHS: A VARIATIONAL APPROACH

• 成果类型: Article
• 署名作者: Mariadassou, Mahendra; Robin, Stephane; Vacher, Corinne
• 署名单位: Universite Paris Saclay; AgroParisTech; INRAE; Universite de Bordeaux; INRAE
• 刊物名称: ANNALS OF APPLIED STATISTICS
• ISSN/ISSBN: 1932-6157
• DOI: 10.1214/10-AOAS361
• 发表日期: 2010
• 页码: 715-742
• 关键词: phylogenetic constraints; Mixture Model; adaptation; EVOLUTION

摘要

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.