TY - GEN
T1 - A Hybrid Bayesian Network Structure Learning Algorithm in Equivalence Class Space
AU - Liu, Xiaohan
AU - Gao, Xiaoguang
AU - Ru, Xinxin
AU - Wang, Zidong
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Greedy equivalence search (GES) is a well-known Bayesian network structure learning algorithm in equivalence class space (E-space). However, the extensive search space limits the efficiency of GES. In this paper, we propose a hybrid method to improve GES. We use mutual information to determine the strongly connected components (SCCs) graph. The SCCs graph is converted to E-space, and we take it as the initial graph of GES. The experiments reveal that our proposed approach significantly prunes the search space of GES and improves the efficiency of GES. Compared with the state-of-The-Art methods, our method also has excellent accuracy.
AB - Greedy equivalence search (GES) is a well-known Bayesian network structure learning algorithm in equivalence class space (E-space). However, the extensive search space limits the efficiency of GES. In this paper, we propose a hybrid method to improve GES. We use mutual information to determine the strongly connected components (SCCs) graph. The SCCs graph is converted to E-space, and we take it as the initial graph of GES. The experiments reveal that our proposed approach significantly prunes the search space of GES and improves the efficiency of GES. Compared with the state-of-The-Art methods, our method also has excellent accuracy.
KW - Bayesian network
KW - greedy equivalence search
KW - strongly connected components
KW - structure learning
UR - https://www.scopus.com/pages/publications/85166244811
U2 - 10.1109/ICCRE57112.2023.10155599
DO - 10.1109/ICCRE57112.2023.10155599
M3 - 会议稿件
AN - SCOPUS:85166244811
T3 - 2023 8th International Conference on Control and Robotics Engineering, ICCRE 2023
SP - 1
EP - 4
BT - 2023 8th International Conference on Control and Robotics Engineering, ICCRE 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 8th International Conference on Control and Robotics Engineering, ICCRE 2023
Y2 - 21 April 2023 through 23 April 2023
ER -