High-dimensional Bayesian network classification with network global-local shrinkage priors

DOI10.1214/23-BA1378arXiv2009.11401OpenAlexW3088093133MaRDI QIDQ6203344FDOQ6203344

Abel Rodriguez, Sharmistha Guha

Publication date: 27 February 2024

Published in: Bayesian Analysis (Search for Journal in Brave)

Abstract: This article proposes a novel Bayesian classification framework for networks with labeled nodes. While literature on statistical modeling of network data typically involves analysis of a single network, the recent emergence of complex data in several biological applications, including brain imaging studies, presents a need to devise a network classifier for subjects. This article considers an application from a brain connectome study, where the overarching goal is to classify subjects into two separate groups based on their brain network data, along with identifying influential regions of interest (ROIs) (referred to as nodes). Existing approaches either treat all edge weights as a long vector or summarize the network information with a few summary measures. Both these approaches ignore the full network structure, may lead to less desirable inference in small samples and are not designed to identify significant network nodes. We propose a novel binary logistic regression framework with the network as the predictor and a binary response, the network predictor coefficient being modeled using a novel class global-local shrinkage priors. The framework is able to accurately detect nodes and edges in the network influencing the classification. Our framework is implemented using an efficient Markov Chain Monte Carlo algorithm. Theoretically, we show asymptotically optimal classification for the proposed framework when the number of network edges grows faster than the sample size. The framework is empirically validated by extensive simulation studies and analysis of a brain connectome data.

Full work available at URL: https://arxiv.org/abs/2009.11401

zbMATH Keywords

posterior consistencynode selectionglobal-local shrinkage priorhigh-dimensional binary regressionbrain connectomenetwork predictor

Mathematics Subject Classification ID

Statistics (62-XX)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Empirical Bayes posterior concentration in sparse high-dimensional linear models
• High-dimensional multivariate posterior consistency under global-local shrinkage priors
• Understanding predictive information criteria for Bayesian models
• Bayesian data analysis.
• Estimation and Prediction for Stochastic Blockstructures
• The horseshoe estimator for sparse signals
• The Bayesian Lasso
• Bayesian Inference for Logistic Models Using Pólya–Gamma Latent Variables
• Bayes and empirical-Bayes multiplicity adjustment in the variable-selection problem
• Markov Graphs
• Bilinear Mixed-Effects Models for Dyadic Data
• Latent Space Approaches to Social Network Analysis
• Joint modeling of longitudinal relational data and exogenous variables
• Graph kernels
• A Bernstein-von Mises theorem for smooth functionals in semiparametric models
• The horseshoe estimator: posterior concentration around nearly black vectors
• Bayesian discriminant analysis using a high dimensional predictor
• Needles and straw in a haystack: posterior concentration for possibly sparse sequences
• Posterior consistency in linear models under shrinkage priors
• Generalized double Pareto shrinkage
• Posterior consistency of Gaussian process prior for nonparametric binary regression
• Modeling the dynamics of social networks using Bayesian hierarchical blockmodels
• Bayesian inference and testing of group differences in brain networks
• Bayesian Regression With Undirected Network Predictors With an Application to Brain Connectome Data
• Needles and straw in a haystack: robust confidence for possibly sparse sequences
• Network classification with applications to brain connectomics
• Lasso meets horseshoe: a survey
• Posterior contraction in sparse generalized linear models
• Ultra high-dimensional multivariate posterior contraction rate under shrinkage priors
• Nearly optimal Bayesian shrinkage for high-dimensional regression
• Contraction properties of shrinkage priors in logistic regression
• Shuffled graph classification: theory and connectome applications

This page was built for publication: High-dimensional Bayesian network classification with network global-local shrinkage priors

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6203344)