期刊文献+

一种从不完备关系数据中学习PRM的方法

An Approach to Learning PRM from Incomplete Relational Data
下载PDF
导出
摘要 现有的关系学习研究都是基于完备数据进行的,而现实问题中,数据通常是不完备的.提出一种从不完备关系数据中学习概率关系模型(probabilistic relational models,简称PRMs)的方法——MLTEC(maximum likelihood tree and evolutionary computing method).首先,随机填充不完备关系数据得到完备关系数据.然后从每个随机填充后的数据样本中分别生成最大似然树并作为初始PRM网络,再利用进化过程中最好的网络结构反复修正不完备数据集,最后得到概率关系模型.实验结果显示,MLTEC方法能够从不完备关系数据中学习到较好的概率关系模型. Existing relational learning approaches usually work on complete relational data. However, in real-world applications, data are often incomplete. This paper proposes the MLTEC (maximum likelihood tree and evolutionary computing method) method to learn structures of the probabilistic relational models (PRMs) from incomplete relational data. The incomplete relational data are filled randomly at first, and a maximum likelihood tree (MLT) is generated from each completed data sample. This population of MLTs is then evolved through an evolutionary computing process, and the incomplete data are modified by using the best evolved structure in each generation. As a result, the probabilistic structure is learned. Experimental results show that the MLTEC method can learn good structures from incomplete relational data.
出处 《软件学报》 EI CSCD 北大核心 2008年第1期73-81,共9页 Journal of Software
基金 Supported by the National Natural Science Foundation of China under Grant Nos.60635030 60473046 (国家自然科学基金) the China Postdoctoral Science Foundation under Grant No.20060390921 (中国博士后科学基金) the Jiangsu Planned Projects for Postdoctoral Research Funds of China under Grant No.0601017B (江苏省博士后科研资助计划)
关键词 机器学习 关系学矾不完备数据 概率关系模型 最大似然树 进化计算 machine learning relational learning incomplete data probabilistic relational model maximum likelihood tree evolutionary computing
  • 相关文献

参考文献1

二级参考文献11

  • 11.Chickering D. Learning equivalence classes of Bayesian networks structures. In: Horvitz E, Jensen F ed. Proceedings of the 12th Conference on Uncertainty in Artificial Intelligence. San Francisco, CA: Morgan Kaufmann Publishers, Inc., 1996. 54~61
  • 22.Geriger D, Hekerman D. A charactererization of the Dirichlet distribution with application to learning Bayesian networks. In: Besnard P, Hanks S eds. Proceedings of the 11th Conference on Uncertainty in Artificial Intelligence. Morgan Kaufmann Publishers Inc., 1995. 196~207
  • 33.Heckman D. A Bayesian approach for learning causal networks. In: Besnard P, Hanks S eds. Proceedings of the 11th Conference on Uncertainty in Artificial Intelligence. San Francisco, CA: Morgan Kaufmann Publishers, Inc., 1995. 285~295
  • 44.Heckman D, Geiger D, Chickering D. Learning Bayesian networks: the combination of knowledge and statistical data. Machine Learning, 1995,20(3):197~243
  • 55.Heckman D, Shachter R. Decision-Theoretic foundations for causal reasoning. Journal of Artificial Intelligence Research, 1995,3:405~430
  • 66.Heckman D, Mandani A, Wellman M. Real-World applications of Bayesian networks. Communications of the ACM, 1995,38(3):38~45
  • 77.Buntine W. Theory refinement on Bayesian networks. In: Proceedings of the 7th Conference on Uncertainty in Artificial Intelligence. Los Angeles, CA: Morgan Kaufmann Publishers, Inc., 1991. 52~61
  • 88.Cooper G, Herskovits E. A Bayesian method for the introduction of probabilistic networks from data. Machine Learning, 1992,9(4):309~347
  • 99.Russell S, Binder J, Koller D et al. Local learning in probabilistic networks with hidden variables. In: Cooper G F, Moral S ed. Proceedings of the 14th International Joint Conference on Artificial Intelligence. San Francisco, CA: Morgan Kaufmann Publishers, Inc., 1998. 1146~1152
  • 101999-03-15

共引文献99

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部