Blankets joint posterior score for learning Markov network structures

DOI10.1016/J.IJAR.2017.10.018zbMATH Open1423.68390arXiv1608.02315OpenAlexW2610828942MaRDI QIDQ1687296FDOQ1687296

Authors: Federico Schlüter, Yanela Strappa, Diego H. Milone, Facundo Bromberg 

Publication date: 22 December 2017

Published in: International Journal of Approximate Reasoning (Search for Journal in Brave)

Abstract: Markov networks are extensively used to model complex sequential, spatial, and relational interactions in a wide range of fields. By learning the structure of independences of a domain, more accurate joint probability distributions can be obtained for inference tasks or, more directly, for interpreting the most significant relations among the variables. Recently, several researchers have investigated techniques for automatically learning the structure from data by obtaining the probabilistic maximum-a-posteriori structure given the available data. However, all the approximations proposed decompose the posterior of the whole structure into local sub-problems, by assuming that the posteriors of the Markov blankets of all the variables are mutually independent. In this work, we propose a scoring function for relaxing such assumption. The Blankets Joint Posterior score computes the joint posterior of structures as a joint distribution of the collection of its Markov blankets. Essentially, the whole posterior is obtained by computing the posterior of the blanket of each variable as a conditional distribution that takes into account information from other blankets in the network. We show in our experimental results that the proposed approximation can improve the sample complexity of state-of-the-art scores when learning complex networks, where the independence assumption between blanket variables is clearly incorrect.

Full work available at URL: https://arxiv.org/abs/1608.02315

Recommendations

• Improving structure MCMC for Bayesian networks through Markov blanket resampling
• Using Markov blankets for causal structure learning
• Marginal pseudo-likelihood learning of discrete Markov network structures
• Structure learning of contextual Markov networks using marginal pseudo-likelihood
• The IBMAP approach for Markov network structure learning
• Approximate structure learning for large Bayesian networks
• scientific article; zbMATH DE number 5183798

zbMATH Keywords

structure learningMarkov networkscoring functionblankets posteriorirregular structures

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• The University of Florida sparse matrix collection
• Causation, prediction, and search
• The Libra toolkit for probabilistic models
• Title not available (Why is that?)
• Title not available (Why is that?)
• Hyper Markov laws in the statistical analysis of decomposable graphical models
• Decomposition of maximum likelihood in mixed graphical interaction models
• Probabilistic graphical models.
• Some Methods for Strengthening the Common χ 2 Tests
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Local causal and Markov blanket induction for causal discovery and feature selection for classification. Part I: Algorithms and empirical evaluation
• Machine learning in complex networks
• Title not available (Why is that?)
• Improving Markov network structure learning using decision trees
• Efficient Markov Network Structure Discovery Using Independence Tests
• The IBMAP approach for Markov network structure learning
• Markov Network-Based Unified Classifier for Face Recognition

Cited In (1)

• Efficient score-based Markov blanket discovery

Uses Software

• MatrixMarket
• SparseMatrix
• Harwell-Boeing sparse matrix collection
• TETRAD
• Libra
• XMRF

This page was built for publication: Blankets joint posterior score for learning Markov network structures

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1687296)