Ou Deng, Shoji Nishimura, Atsushi Ogihara, Qun Jin
{"title":"利用相对影响分层发现进化因果,实现可解释的数据分析","authors":"Ou Deng, Shoji Nishimura, Atsushi Ogihara, Qun Jin","doi":"arxiv-2404.16361","DOIUrl":null,"url":null,"abstract":"This study proposes Evolutionary Causal Discovery (ECD) for causal discovery\nthat tailors response variables, predictor variables, and corresponding\noperators to research datasets. Utilizing genetic programming for variable\nrelationship parsing, the method proceeds with the Relative Impact\nStratification (RIS) algorithm to assess the relative impact of predictor\nvariables on the response variable, facilitating expression simplification and\nenhancing the interpretability of variable relationships. ECD proposes an\nexpression tree to visualize the RIS results, offering a differentiated\ndepiction of unknown causal relationships compared to conventional causal\ndiscovery. The ECD method represents an evolution and augmentation of existing\ncausal discovery methods, providing an interpretable approach for analyzing\nvariable relationships in complex systems, particularly in healthcare settings\nwith Electronic Health Record (EHR) data. Experiments on both synthetic and\nreal-world EHR datasets demonstrate the efficacy of ECD in uncovering patterns\nand mechanisms among variables, maintaining high accuracy and stability across\ndifferent noise levels. On the real-world EHR dataset, ECD reveals the\nintricate relationships between the response variable and other predictive\nvariables, aligning with the results of structural equation modeling and\nshapley additive explanations analyses.","PeriodicalId":501033,"journal":{"name":"arXiv - CS - Symbolic Computation","volume":"50 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Evolutionary Causal Discovery with Relative Impact Stratification for Interpretable Data Analysis\",\"authors\":\"Ou Deng, Shoji Nishimura, Atsushi Ogihara, Qun Jin\",\"doi\":\"arxiv-2404.16361\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This study proposes Evolutionary Causal Discovery (ECD) for causal discovery\\nthat tailors response variables, predictor variables, and corresponding\\noperators to research datasets. Utilizing genetic programming for variable\\nrelationship parsing, the method proceeds with the Relative Impact\\nStratification (RIS) algorithm to assess the relative impact of predictor\\nvariables on the response variable, facilitating expression simplification and\\nenhancing the interpretability of variable relationships. ECD proposes an\\nexpression tree to visualize the RIS results, offering a differentiated\\ndepiction of unknown causal relationships compared to conventional causal\\ndiscovery. The ECD method represents an evolution and augmentation of existing\\ncausal discovery methods, providing an interpretable approach for analyzing\\nvariable relationships in complex systems, particularly in healthcare settings\\nwith Electronic Health Record (EHR) data. Experiments on both synthetic and\\nreal-world EHR datasets demonstrate the efficacy of ECD in uncovering patterns\\nand mechanisms among variables, maintaining high accuracy and stability across\\ndifferent noise levels. On the real-world EHR dataset, ECD reveals the\\nintricate relationships between the response variable and other predictive\\nvariables, aligning with the results of structural equation modeling and\\nshapley additive explanations analyses.\",\"PeriodicalId\":501033,\"journal\":{\"name\":\"arXiv - CS - Symbolic Computation\",\"volume\":\"50 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-04-25\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Symbolic Computation\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2404.16361\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Symbolic Computation","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2404.16361","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Evolutionary Causal Discovery with Relative Impact Stratification for Interpretable Data Analysis
This study proposes Evolutionary Causal Discovery (ECD) for causal discovery
that tailors response variables, predictor variables, and corresponding
operators to research datasets. Utilizing genetic programming for variable
relationship parsing, the method proceeds with the Relative Impact
Stratification (RIS) algorithm to assess the relative impact of predictor
variables on the response variable, facilitating expression simplification and
enhancing the interpretability of variable relationships. ECD proposes an
expression tree to visualize the RIS results, offering a differentiated
depiction of unknown causal relationships compared to conventional causal
discovery. The ECD method represents an evolution and augmentation of existing
causal discovery methods, providing an interpretable approach for analyzing
variable relationships in complex systems, particularly in healthcare settings
with Electronic Health Record (EHR) data. Experiments on both synthetic and
real-world EHR datasets demonstrate the efficacy of ECD in uncovering patterns
and mechanisms among variables, maintaining high accuracy and stability across
different noise levels. On the real-world EHR dataset, ECD reveals the
intricate relationships between the response variable and other predictive
variables, aligning with the results of structural equation modeling and
shapley additive explanations analyses.