Causal constraint pruning for exact learning of Bayesian network structure
- 1 August 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Journal of Systems Engineering and Electronics
- Vol. 32 (4), 854-872
- https://doi.org/10.23919/jsee.2021.000074
Abstract
How to improve the efficiency of exact learning of the Bayesian network structure is a challenging issue. In this paper, four different causal constraints algorithms are added into score calculations to prune possible parent sets, improving state-of-the-art learning algorithms' efficiency. Experimental results indicate that exact learning algorithms can significantly improve the efficiency with only a slight loss of accuracy. Under causal constraints, these exact learning algorithms can prune about 70% possible parent sets and reduce about 60% running time while only losing no more than 2% accuracy on average. Additionally, with sufficient samples, exact learning algorithms with causal constraints can also obtain the optimal network. In general, adding max-min parents and children constraints has better results in terms of efficiency and accuracy among these four causal constraints algorithms.Keywords
This publication has 14 references indexed in Scilit:
- A survey on Bayesian network structure learning from dataProgress in Artificial Intelligence, 2019
- Entropy-based pruning for learning Bayesian networks using BICArtificial Intelligence, 2018
- Approximate structure learning for large Bayesian networksMachine Learning, 2018
- Empirical hardness of finding optimal Bayesian network structures: algorithm selection and runtime predictionMachine Learning, 2017
- Learning Bayesian network structures under incremental construction curriculaNeurocomputing, 2017
- A new hybrid method for learning bayesian networks: Separation and reunionKnowledge-Based Systems, 2017
- Integer Linear Programming for the Bayesian network structure learning problemArtificial Intelligence, 2017
- Bayesian Network Structure Learning with Integer Programming: Polytopes, Facets and ComplexityJournal of Artificial Intelligence Research, 2017
- Machine Learning of Bayesian Networks Using Constraint ProgrammingPublished by Springer Science and Business Media LLC ,2015
- The max-min hill-climbing Bayesian network structure learning algorithmMachine Learning, 2006