A Cooperative Coevolutionary Genetic Algorithm for Learning Bayesian Network Structures

TL;DR

This paper introduces a cooperative coevolutionary genetic algorithm designed to learn Bayesian network structures from data, effectively decomposing the problem into node ordering and connectivity, and demonstrating superior performance over existing methods.

Contribution

The paper presents a novel coevolutionary genetic algorithm that decomposes Bayesian network structure learning into subproblems, improving over traditional algorithms like K2.

Findings

Outperforms the K2 algorithm in simulations

Effective decomposition into subproblems

Demonstrates improved accuracy and efficiency

Abstract

We propose a cooperative coevolutionary genetic algorithm for learning Bayesian network structures from fully observable data sets. Since this problem can be decomposed into two dependent subproblems, that is to find an ordering of the nodes and an optimal connectivity matrix, our algorithm uses two subpopulations, each one representing a subtask. We describe the empirical results obtained with simulations of the Alarm and Insurance networks. We show that our algorithm outperforms the deterministic algorithm K2.