Finding Community Structure of Bayesian Networks by Improved K-Means Algorithm

Many Bayesian networks display community structure; study community structure helps to reduce the complexity of learning Bayesian network in high-dimensional data. To find the community structure of Bayesian networks, this paper proposes an improved K-means algorithm by incorporating the mutual information into the K-means algorithm and modifying the iteration conditions. Experiments show that the proposed algorithm is suitable for block tasks of Bayesian network. Compared with FastNewman algorithm, the proposed algorithm can obtain accurate results in a shorter time.