Uncovering latent structure in valued graphs: A variational approach

Abstract

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.

Published in at http://dx.doi.org/10.1214/10-AOAS361 the Annals of Applied Statistics (http://www.imstat.org/aoas/) by the Institute of Mathematical Statistics (http://www.imstat.org)

References in corpus (8)

• Emergence of scaling in random networks
• Statistical mechanics of complex networks
• Community structure in social and biological networks
• Fast algorithm for detecting community structure in networks
• Consistency of spectral clustering
• A Bayesian Approach to Network Modularity
• Uncovering latent structure in valued graphs: A variational approach
• A Generalized Mean Field Algorithm for Variational Inference in Exponential Families

Cited by in corpus (57)

• Exponential-Family Random Graph Models for Valued Networks
• Pseudo-likelihood methods for community detection in large sparse networks
• Hierarchical Block Structures and High-resolution Model Selection in Large Networks
• Efficient Monte Carlo and greedy heuristic for the inference of stochastic block models
• Stochastic blockmodels with growing number of classes
• Uncovering latent structure in valued graphs: A variational approach
• Inferring the mesoscale structure of layered, edge-valued and time-varying networks
• Model selection and hypothesis testing for large-scale network models with overlapping groups
• Adapting the Stochastic Block Model to Edge-Weighted Networks
• The Stochastic Topic Block Model for the Clustering of Vertices in Networks with Textual Edges
• Model-based clustering of large networks
• Mixed-Membership of Experts Stochastic Blockmodel
• Inferring sparse Gaussian graphical models with latent structure
• Convergence of the groups posterior distribution in latent or stochastic block models
• Nine Quick Tips for Analyzing Network Data
• Adapting Stochastic Block Models to Power-Law Degree Distributions
• Strategies for online inference of model-based clustering in large and growing networks
• Variational Bayes model averaging for graphon functions and motif frequencies inference in W-graph models
• Blockmodels: A R-package for estimating in Latent Block Model and Stochastic Block Model, with various probability functions, with or without covariates
• Algorithmic detectability threshold of the stochastic block model
• A Stochastic Block Model Approach for the Analysis of Multilevel Networks: an Application to the Sociology of Organizations
• Model selection and clustering in stochastic block models with the exact integrated complete data likelihood
• Hierarchical clustering with discrete latent variable models and the integrated classification likelihood
• Online Bayesian changepoint detection for network Poisson processes with community structure
• Stochastic Block Models for Multiplex networks: an application to networks of researchers
• A Tractable Fully Bayesian Method for the Stochastic Block Model
• Consistency and Asymptotic Normality of Stochastic Block Models Estimators from Sampled Data
• Hierarchical community detection by recursive partitioning
• Goodness of fit of logistic models for random graphs
• Variational Inference for Latent Space Models for Dynamic Networks
• Motif-Based Spectral Clustering of Weighted Directed Networks
• Wmixnet: Software for Clustering the Nodes of Binary and Valued Graphs using the Stochastic Block Model
• GANC: Greedy Agglomerative Normalized Cut
• Hierarchical network models for structured exchangeable interaction processes
• Block models for multipartite networks.Applications in ecology and ethnobiology
• A simpler spectral approach for clustering in directed networks
• Clustering in networks with the collapsed Stochastic Block Model
• New consistent and asymptotically normal estimators for random graph mixture models
• A semiparametric extension of the stochastic block model for longitudinal networks
• Impact of the mesoscale structure of a bipartite ecological interaction network on its robustness through a probabilistic modeling
• The Strength of Arcs and Edges in Interaction Networks: Elements of a Model-Based Approach
• A Social Network Analysis of Articles on Social Network Analysis
• Learning common structures in a collection of networks. An application to food webs
• Bayesian inference for network Poisson models
• Community Detection in Weighted Multilayer Networks with Ambient Noise
• Mixture Models and Networks -- Overview of Stochastic Blockmodelling
• On role extraction for digraphs via neighbourhood pattern similarity
• Detecting Hierarchical Changes in Latent Variable Models
• On Equivalence of Likelihood Maximization of Stochastic Block Model and Constrained Nonnegative Matrix Factorization
• Variational Inference for Stochastic Block Models from Sampled Data
• Spatially-constrained clustering of ecological networks
• bioSBM: a random graph model to integrate epigenomic data in chromatin structure prediction
• Clustering on the Edge: Learning Structure in Graphs
• Clustering based on Random Graph Model embedding Vertex Features
• Community Detection by $L_0$-penalized Graph Laplacian
• Model Selection in Overlapping Stochastic Block Models
• Estimation and Model Selection for Model-Based Clustering with the Conditional Classification Likelihood