Bayesian Network Parameter Learning Method Based on Transfer Learning

doi:10.12068/j.issn.1005-3026.2021.04.008

Abstract

Abstract: In order to solve the problem that there are many restrictions on the source domain and the target domain in the process of Bayesian network parameter transfer， a unified framework based on Bayesian network parameter transfer learning was proposed under the condition of considering multiple information forms of source domain and target domain. The method considers the role of source domain structure and data volume in the migration. On the basis of structural similarity， the influence of alternative source domain data volume on parameter migration was discussed. The balance coefficient related to the target domain data was introduced in the migration process. According to the balance coefficient， the target domain data was linked with the migration process to realize the automatic adjustment of the balance coefficient. The Asia network verifies the accuracy of the method in this paper.

Key words: Bayesian network; parameter learning; transfer learning; structural similarity; equilibrium coefficient

CLC Number:

TP311
TP181

WANG Shu， GUAN Zhan-xu， WANG Jing， SUN Xiao-hui. Bayesian Network Parameter Learning Method Based on Transfer Learning[J]. Journal of Northeastern University(Natural Science), 2021, 42(4): 509-515.

References

[1]Amin M T，Khan F，Ahmed S，et al.A novel data-driven methodology for fault detection and dynamic risk assessment［J］.Canadian Journal of Chemical Engineering， 2020.http://doi.org/10.1002/cjce.23760
[2]Scanagatta M，Corani G，Zaffalon M，et al.Efficient learning of bounded-tree width Bayesian networks from complete and incomplete data sets［J］.International Journal of Approximate Reasoning，2018，95:152-166.
[3]Incerti D，Curtis J R，Shafrin J，et al.A flexible open-source decision model for value assessment of biologic treatment for rheumatoid arthritis ［J］.Pharmaco Economics，2019，37(1):829-843.
[4]Amin M T，Khan F，Imtiza S.Fault detection and pathway analysis using a dynamic Bayesian network［J］.Chemical Engineering Science，2019，195(23):777-790.
[5]Sun H W，Xie X F，Sun T，et al.Threat assessment method of warships formation air defense based on DBN under the condition of small sample data missing［J］.Systems Engineering and Electronics，2019，41(6):1300-1308.
[6]Li Z D，Liao S Z.Bayesian network parameter learning method on small samples［J］.Computer Engineering，2016，42(8):153-159，165．
[7]Zeng Q，Huang Z，Wei S H.Bayesian network parameter learning method based on expert priori knowledge and monotonic constraints［J］.Systems Engineering and Electronics，2020，42(3):646-652.
[8]郭文强，徐成，肖秦琨，等.基于变权重迁移学习的BN参数学习算法［J］.计算机应用研究，2020，38(1).http://doi.org/10.19734/j.issn.1001-3695.2019.10.0600.(Guo Wen-qiang，Xu Cheng，Xiao Qin-kun，et al.BN parameter learning algorithm based on dynamic weighted transfer learning［J］.Application Research of Computers，2020，38(1).http://doi.org/10.19734/j.issn.1001-3695.2019.10.0600.)
[9]Yuan P，Sun Y F，Li H，et al.Abnormal condition identification modeling method based on Bayesian network parameters transfer learning for the electro-fused magnesia smelting process［J］.IEEE Access，2019，7:149764-149775.
[10]闫浩，王福利，孙钰沣，等.基于贝叶斯网络参数迁移学习的电熔镁炉异常工况识别［J］.自动化学报，2020.https://doi.org/10.16383/j.aas.c200104.)(Yan Hao，Wang Fu-Li，Sun Yu-feng，et al.Abnormal condition identification based on Bayesian network parameters transfer learning for the electro-fused magnesia［J］.Acta Automatica Sinica，2020.https://doi.org/10.16383/j.aas.c200104.)
[11]Liu A H，Cheng Z H，Jiang J.Bayesian network learning for classification via transfer method［J］.IEEE Computer Society，2019:1102-1109.
[12]Li H，Wang F L，Li H R，et al.Safety control modeling method based on Bayesian network transfer［J］.Knowledge-Based Systems，2020.https:doi.org/10.1016/j.knosys.2019.105297.
[13]Gao X G，Ye S M，Di R H，et al.Bayesian network structure learning based on fusion prior method［J］.Systems Engineering and Electronics，2018，40(4):790-796.

[1]	LIU Qiong， LUO Qing， PENG Shao-wu. RoI Extraction for Vehicular Thermal Infrared Pedestrian Detection [J]. Journal of Northeastern University Natural Science, 2020, 41(8): 1083-1090.
[2]	XU Hong-fei， GU Yu， YU Ge. Moving k Nearest Neighbor Query with Spatial Diversity Constraints [J]. Journal of Northeastern University Natural Science, 2020, 41(7): 913-919.
[3]	YUAN Zhong-chen， MA Zong-min. Retrieval of UML Class Diagrams Based on Semantics and Structure [J]. Journal of Northeastern University Natural Science, 2020, 41(1): 23-28.
[4]	YU Chang-yong， LI Miao-miao， ZHAO Chu， MA Hai-tao. A Novel Similarity Verification Algorithm Under Edit Distance Limitation [J]. Journal of Northeastern University Natural Science, 2019, 40(11): 1543-1548.
[5]	ZHANG Qiang， QIAO Jian-zhong. Design and Implement of TEE-Based Trusted Storage System [J]. Journal of Northeastern University Natural Science, 2019, 40(8): 1080-1086.
[6]	LIU Jun， LENG Fang-ling， LI Shi-qi， BAO Yu-bin. A Distributed File System Based on HDFS [J]. Journal of Northeastern University Natural Science, 2019, 40(6): 795-800.
[7]	MA Hai-tao， QI Shi，YU Chang-yong， ZHAO Yu-hai. Frequency-Based Seed Selection Algorithm for Read Mapping [J]. Journal of Northeastern University Natural Science, 2019, 40(5): 609-613.
[8]	YU Chang-yong， GAO Ming， BAI Lu-yi， ZHAO Yu-hai. A String Collection Indexing Method with String Length and Position Constraint [J]. Journal of Northeastern University Natural Science, 2018, 39(7): 959-963.
[9]	KOU Yue， XU Hong-bin， SHEN De-rong， NIE Tie-zheng. A Topic Domain Identification Model Combining Local and Global Characteristics [J]. Journal of Northeastern University Natural Science, 2018, 39(2): 176-180.
[10]	LIN Chuan， ZHAO Hai， BI Yuan-guo， CAI Wei. Design and Implementation of a QoS-Enabled Measuring and Routing System Based on SDNs [J]. Journal of Northeastern University Natural Science, 2017, 38(8): 1069-1074.
[11]	PANG Jun， GU Yu， YU Ge. A Similarity Search Technique for Graph Set [J]. Journal of Northeastern University:Natural Science, 2017, 38(5): 625-629.
[12]	BAI Lu-yi， JIA Wei-jia， CAO Xing-ru. CDT-based Determining Method of Topological Relations for Spatiotemporal Regions [J]. Journal of Northeastern University Natural Science, 2017, 38(4): 481-485.
[13]	ZHAO Zhen， MA Zong-min. Research on the Similarity of Fuzzy XML Documents and Fuzzy DTD [J]. Journal of Northeastern University Natural Science, 2017, 38(2): 200-204.
[14]	LIN Xiao-qing， MA Zong-min. RDF Keyword Search by the Condensed Entity Summary Graph [J]. Journal of Northeastern University Natural Science, 2017, 38(1): 22-26.
[15]	DU Yue-feng， SHEN De-rong， ZHANG Liang， YU Ge. A Consistency Cleaning Method Based on Content-related Conditional Functional Dependencies [J]. Journal of Northeastern University Natural Science, 2016, 37(12): 1683-1687.