High-dimensional causal discovery based on heuristic causal partitioning

Hong, Yinghan1,2; Guo, Junping3; Mai, Guizhen1; Lin, Yingqing4; Zhang, Hao5,6; Hao, Zhifeng4; Zheng, Gengzhong7

2023-07-01

10.1007/s10489-023-04530-7

APPLIED INTELLIGENCE   影响因子和分区

0924-669X

1573-7497

Causal discovery is one of the most important research directions in the field of machine learning, aiming to discover the underlying causal relationships in the observed data. In practice, the time complexity of causal discovery will grow exponentially with increasing variables. To alleviate this problem, many methods based on divide-and-conquer strategies have been proposed. Existing methods usually partition the variables heuristically using scattered variables to achieve the dividing process, which makes it difficult to minimize vertex cut-set C and then leads to diminished causal discovery performance. In this work, we design an elaborated causal partition strategy called Causal Partition Base Graph (CPBG) to solve this problem. CPBG uses a set of low-order conditional independence (CI) tests to construct a rough skeleton S corresponding to the observed data and takes a heuristic method to search S for the optimal vertex cut-set C. Then the observed data can be partitioned into multiple variable subsets. We therefore can run a causal discovery method on each part and finally obtain the complete causal structure by merging the partial results. The proposed method is evaluated by various real-world causal datasets. Experimental results show that the CPBG method outperforms its existing counterparts, which proves that the method can support more effective and efficient causal discovery. The source code of the proposed method and all experimental results are available at .

Causal discovery High-dimensionality Conditional independence tests Graph theory

SCI

英语

其他

National Natural Science Foundation["61971052","62006051"] ; National Key R amp; D Program of China[2020YFC2004300] ; Science and Technology Planning Project of Guangdong Province, China["2019B101001021","2020B1010010010","Z20077"] ; Project of Young Innovative Talents in Colleges and Universities in Guangdong Province[2020KQNCX049] ; Guangdong Provincial Key Laboratory[2020B121201001] ; Research Project of Guangdong Provincial Department of Education["2021KTSCX070","2021KCXTD038"] ; Guangdong Basic and Applied Basic Research Foundation["2021A1515011995","2022A1515011551"] ; Doctor Starting Fund of Hanshan Normal University, China["QD20190628","QD2021201"] ; Scientific Research Talents Fund of Hanshan Normal University, China[Z19113] ; School of Intelligent Manufacturing Industry of Hanshan Normal University[E22022] ; Scientific research project of Guangdong Provincial Department of Education[2022ZDZX4031] ; Research platform project of Hanshan Normal University[PNB221102] ; Guangdong Provincial Key Laboratory of Data Science and Intelligent Education[2022KSYS003]

Computer Science

Computer Science, Artificial Intelligence

WOS:001030448400002

SPRINGER

ENGINEERING

Web of Science

1.Hanshan Normal Univ, Sch Phys & Elect Engn, Chaozhou 521041, Guangdong, Peoples R China
2.Southern Univ Sci & Technol, Guangdong Prov Key Lab Brain Inspired Intelligent, Shenzhen 518055, Peoples R China
3.Hanshan Normal Univ, Sch Math & Stat, Chaozhou 521041, Guangdong, Peoples R China
4.Shantou Univ, Dept Math, Shantou 515063, Guangdong, Peoples R China
5.Fudan Univ, Sch Comp Sci, Shanghai 200433, Peoples R China
6.Guangdong Univ Petrochem Technol, Sch Comp Sci, Maoming 525000, Guangdong, Peoples R China
7.Hanshan Normal Univ, Sch Comp & Informat Engn, Chaozhou 521041, Guangdong, Peoples R China

Hong, Yinghan,Guo, Junping,Mai, Guizhen,et al. High-dimensional causal discovery based on heuristic causal partitioning[J]. APPLIED INTELLIGENCE,2023,53(20).

Hong, Yinghan.,Guo, Junping.,Mai, Guizhen.,Lin, Yingqing.,Zhang, Hao.,...&Zheng, Gengzhong.(2023).High-dimensional causal discovery based on heuristic causal partitioning.APPLIED INTELLIGENCE,53(20).

Hong, Yinghan,et al."High-dimensional causal discovery based on heuristic causal partitioning".APPLIED INTELLIGENCE 53.20(2023).