a novel bayesian network structure learning algorithm based on maximal information coefficient

ISCAS OpenIR

	a novel bayesian network structure learning algorithm based on maximal information coefficient
	Zhang Yinghua; Hu Qiping; Zhang Wensheng; Liu Jin
	2012
会议名称	2012 IEEE 5th International Conference on Advanced Computational Intelligence, ICACI 2012
会议录名称	2012 IEEE 5th International Conference on Advanced Computational Intelligence, ICACI 2012
页码	862-867
会议日期	October 18, 2012 - October 20, 2012
会议地点	Nanjing, China
收录类别	EI
ISBN	9781467317436
部门归属	(1) State Key Laboratory of Intelligent Control and Management of Complex Systems Institute of Automation Chinese Academy of Sciences BeiJing 100190 China; (2) International School of Software Wuhan University Wuhan 430074 China; (3) State Key Laboratory of Software Engineering Computer School Wuhan University Wuhan 430074 China
摘要	Greedy Equivalent Search (GES) is an effective algorithm for Bayesian network problem, which searches in the space of graph equivalence classes. However, original GES may easily fall into local optimization trap because of empty initial structure. In this paper, An improved GES method is prosposed. It firstly makes a draft of the real network, based on Maximum Information Coefficient (MIC) and conditional independence tests. After this step, many independent relations can be found. To ensure correctness, then this draft is used to be a seed structure of original GES algorithm. Numerical experiment on four standard networks shows that NEtoGS (the number of graph structure, which is equivalent to the God Standard network) has big improvement. Also, the total of learning time are greatly reduced. Therefore, our improved method can relatively quickly determine the structure graph with highest degree of data matching. © 2012 IEEE.; Greedy Equivalent Search (GES) is an effective algorithm for Bayesian network problem, which searches in the space of graph equivalence classes. However, original GES may easily fall into local optimization trap because of empty initial structure. In this paper, An improved GES method is prosposed. It firstly makes a draft of the real network, based on Maximum Information Coefficient (MIC) and conditional independence tests. After this step, many independent relations can be found. To ensure correctness, then this draft is used to be a seed structure of original GES algorithm. Numerical experiment on four standard networks shows that NEtoGS (the number of graph structure, which is equivalent to the God Standard network) has big improvement. Also, the total of learning time are greatly reduced. Therefore, our improved method can relatively quickly determine the structure graph with highest degree of data matching. © 2012 IEEE.
关键词	Artificial Intelligence Equivalence Classes Learning Algorithms
主办者	IEEE Nanjing Section
语种	英语
内容类型	会议论文
URI标识	http://ir.iscas.ac.cn/handle/311060/15944
专题	中国科学院软件研究所
推荐引用方式 GB/T 7714	Zhang Yinghua,Hu Qiping,Zhang Wensheng,et al. a novel bayesian network structure learning algorithm based on maximal information coefficient[C],2012:862-867.