Bayesian Network Structure Learning Approach Based on Searching Local Structure of Strongly Connected Components
文献类型：期刊论文
| 作者 | Zhong, Kunhua1,2,3 ; Chen, Yuwen1,2,3; Zhang, Ju2; Qin, Xiaolin1,3
|
| 刊名 | IEEE ACCESS
 |
| 出版日期 | 2022 |
| 卷号 | 10页码:67630-67638 |
| 关键词 | Bayes methods Approximation algorithms Search problems Directed graphs Heuristic algorithms Periodic structures Random variables Bayesian network structure learning hill climbing search strongly connected component |
| ISSN号 | 2169-3536 |
| DOI | 10.1109/ACCESS.2022.3178842 |
| 通讯作者 | Qin, Xiaolin(qinxl@casit.ac.cn) |
| 英文摘要 | Learning the structure of Bayesian networks is a challenging problem because it is a NP-Hard problem. As an excellent search & score based method, the K2 algorithm strongly depends on the input of global order of all nodes to ensure the result is a directed acyclic graph. And the K2 algorithm searches parents for each node from the nodes before it in the global order. Incorrect node order is likely to result in a wrong structure. In this paper, we propose a new method to avoid the global order by Local structure Searching for Strongly Connected Components with hill climbing method Twice. Firstly, we search the best parent nodes for each node from all the remaining nodes except itself, and form a global directed graph by concatenating the arcs between nodes and their parents. Then, the directed acyclic structure of all the strongly connected components are determined by hill climbing algorithm twice continuously. Finally, we adopt local search method further to get the final result by taking the previous result as a start point. The proposed algorithm is evaluated on several standard benchmark networks with sampled data. Experimental results show that our algorithm outperforms the four compared algorithms in terms of structural Hamming distance, Bayesian information criterion score and their average ranking. |
| 资助项目 | National Key Research and Development Plan of China[2018YFC0116704] ; Sichuan Science and Technology Program of China[2019ZDZX0006] ; Sichuan Science and Technology Program of China[2020YFG0010] ; Sichuan Science and Technology Program of China[2020YFQ0056] ; Science and Technology Service Network Initiative, CAS, China[KFJ-STS-QYZD-2021-21-001] |
| WOS研究方向 | Computer Science ; Engineering ; Telecommunications |
| 语种 | 英语 |
| WOS记录号 | WOS:000819819100001 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 源URL | [http://119.78.100.138/handle/2HOD01W0/15973]  |
| 专题 | 中国科学院重庆绿色智能技术研究院 |
| 通讯作者 | Qin, Xiaolin |
| 作者单位 | 1.Chinese Acad Sci, Chengdu Inst Comp Applicat, Chengdu 610041, Peoples R China 2.Chinese Acad Sci, Chongqing Inst Green & Intelligent Technol, Chongqing 400714, Peoples R China 3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China |
| 推荐引用方式 GB/T 7714 | Zhong, Kunhua,Chen, Yuwen,Zhang, Ju,et al. Bayesian Network Structure Learning Approach Based on Searching Local Structure of Strongly Connected Components[J]. IEEE ACCESS,2022,10:67630-67638. |
| APA | Zhong, Kunhua,Chen, Yuwen,Zhang, Ju,&Qin, Xiaolin.(2022).Bayesian Network Structure Learning Approach Based on Searching Local Structure of Strongly Connected Components.IEEE ACCESS,10,67630-67638. |
| MLA | Zhong, Kunhua,et al."Bayesian Network Structure Learning Approach Based on Searching Local Structure of Strongly Connected Components".IEEE ACCESS 10(2022):67630-67638. |
入库方式： OAI收割
来源：重庆绿色智能技术研究院
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。