STRUCTURE LEARNING OF BAYESIAN NETWORKS BASED ON HYBRID EVOLUTIONARY ALGORITHM WITH ELITE STRATEGY

Structure learning of Bayesian networks is a crucial problem in the area of statistical machine learning and probabilistic graphical models. In this paper, a novel structure learning method for Bayesian network is proposed, which combines genetic algorithm (GA) with particle swarm optimization (PSO), and utilizes elite strategy. It benefits from both advantage of GA in maintaining the diversity of population, and the advantage of PSO in the convergence rate. In addition, in the process of evolution, the elite set strategy is introduced to adjust the maximal number threshold of parents of each node dynamically, prune intelligently and guide mutation operation. The experimental results show the superiority of the proposed approach to state-of-the-art approach.