Decomposition-based Bayesian network structure learning algorithm using local topology information
作者：
Highlights：
• Maximal information coefficient is used to filter useless Markov blanket nodes.
• A path length parameter and relative distance between two nodes are considered.
• Undirected independence graph is quickly built by using local topology information.
• kpath node centrality is used to evaluate the relative importance of all nodes.
• Stop conditions used in the decomposition procedure is provided.
摘要
•Maximal information coefficient is used to filter useless Markov blanket nodes.•A path length parameter and relative distance between two nodes are considered.•Undirected independence graph is quickly built by using local topology information.•kpath node centrality is used to evaluate the relative importance of all nodes.•Stop conditions used in the decomposition procedure is provided.
论文关键词：Bayesian network,Structure learning,Model decomposition,Local neighborhood structure
论文评审过程：Received 14 May 2019, Revised 30 January 2020, Accepted 31 January 2020, Available online 7 February 2020, Version of Record 4 April 2020.
论文官网地址：https://doi.org/10.1016/j.knosys.2020.105602
