Hybrid incremental learning algorithms for bayesian network structures

Hybrid learning can reduce the computational complexity of incremental algorithms for Bayesian network structures significantly. In this paper, a group of hybrid incremental algorithms are proposed. The central idea of these algorithms is to use the polynomial-time constraint-based technique to build a candidate parent set for each domain variable, followed by the hill climbing search procedure to refine the current network structure under the guidance of the candidate parent sets. The experimental results show that, our hybrid incremental algorithms offer considerable computational complexity savings while obtaining better model accuracy compared to the existing incremental algorithms.