• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

J4 ›› 2010, Vol. 32 ›› Issue (9): 122-126.doi: 10.3969/j.issn.1007130X.2010.

• 论文 • 上一篇    下一篇

贝叶斯网结构学习搜索空间分析

贾海洋,陈娟,刘大有   

  1. (吉林大学计算机科学与技术学院,符号计算与知识工程教育部重点实验室,吉林 长春 130012)
  • 收稿日期:2010-03-13 修回日期:2010-06-10 出版日期:2010-09-02 发布日期:2010-09-02
  • 作者简介:贾海洋(1977),男,吉林长春人,博士,讲师,CCF会员(E200014855M),研究方向为贝叶斯网学习、数据挖掘和知识工程;陈娟,博士,讲师,研究方向为时空推理、不确定性推理与知识工程;刘大有,教授,研究方向为知识工程与专家系统、分布式人工智能、多Agent系统、不确定性推理、空间推理、地理信息系统。
  • 基金资助:

    国家自然科学基金资助项目(60496321,60573073,60603030,60773099,60703022);国家863计划资助项目(2006AA10Z245 );教育部博士点基金资助项目(20070183057);中央高校基本科研业务费专项资金资助——吉林大学(421032041421)

Analysis on the Searching Space of  the Bayesian Networks Structure Learning

JIA Haiyang,CHEN Juan,LIU Dayou   

  1. (School of Computer Science and Technology,Key Laboratory for Symbolic Computation and
    Knowledge Engineering of the Ministry of Education,Jilin University,Changchun 130012,China)
  • Received:2010-03-13 Revised:2010-06-10 Online:2010-09-02 Published:2010-09-02

摘要:

贝叶斯网结构学习是一个NP难题,提高学习效率是重要研究问题之一。贝叶斯网结构空间的规模随节点(随机变量)数呈指数增加,选择适当的结构空间可以提高学习效率。本文对贝叶斯网结构空间进行定性和定量分析,对比有向图空间、贝叶斯网空间和马尔科夫等价类空间的规模和特点。通过实验数据分析先验结构空间约束对降低结构空间规模的效率,给出约束参数的选择区间。为贝叶斯网结构学习选择搜索空间和确定约束参数提供理论支持,从而提高学习效率。

关键词: 贝叶斯网, 结构学习, 搜索空间, 马尔可夫等价

Abstract:

Structure learning of the Bayesian networks is a NP hard problem, and improving the efficiency of structure learning is one of the most important problems. The size of a searching space increases exponentially with the number of vertexes, and choosing and limiting the searching space of structure learning can improve the efficiency of a learning algorithm. This paper gives a qualitative and quantitive analysis on the searching space, compares the sizes and characteristics of the directed graph, the directed acyclic graph and the Markov equivalence class space. Based on the experiment data, we analyse the efficiency of constraining the prior structure space, and give an advice on choosing the parameters. These analyses are helpful when choosing the searching space and defining the parameters of constraints, thus  improving the efficiency of structure learning.

Key words: Bayesian networks;structural learning;searching space;Markov equivalence