Counterfactual inference to predict causal knowledge graph for relational transfer learning by assimilating expert knowledge --Relational feature transfer learning algorithm. (January 2022)

• Record Type: Journal Article
• Authors: Li, Jiarui; Horiguchi, Yukio; Sawaragi, Tetsuo
• Is Part Of: Advanced engineering informatics. Volume 51(2022)
• Publication Date: 2022-01
• Subjects: Transfer learning -- Causality -- Counterfactual inference -- Knowledge networks -- Explainable machine learning; AHI Apnea Hypopnea Index -- CEA Assumption of Constant Effect -- CFA Confirmatory Factor Analysis -- CORAL CORelation Alignment -- EFA Exploratory Factor Analysis -- EMR Electronic Medical Records -- FPCI Fundamental Problem of Causal Inference -- GA Genetic Algorithm -- GoF Goodness of Fit -- HA Assumption of Homogeneity -- ICU Intensive Care Unit -- KG(s) Knowledge Graph(s) -- LTL Language-bias Transfer Learning -- ML Machine Learning -- OSA Obstructive Sleep Apnea -- RF-TL Relational Feature Transfer Learning -- SEM-EML Structural Equation Modeling-Explainable Machine Learning model -- SF_36 36-Item Short Form Survey -- SUTVA Stable Unit Treatment Value Assumption -- TCA Transfer Component Analysis -- TL Transfer Learning; Computer-aided engineering -- Periodicals; Engineering -- Data processing -- Periodicals; 620.00285
• DOI: 10.1016/j.aei.2021.101516
• Languages: English
• ISSNs: 1474-0346

Abstract

Abstract: Transfer learning (TL) is a machine learning (ML) method in which knowledge is transferred from the existing models of related problems to the model for solving the problem at hand. Relational TL enables the ML models to transfer the relationship networks from one domain to another. However, it has two critical issues. One is determining the proper way of extracting and expressing relationships among data features in the source domain such that the relationships can be transferred to the target domain. The other is how to do the transfer procedure. Knowledge graphs (KGs) are knowledge bases that use data and logic to graph-structured information; they are helpful tools for dealing with the first issue. The proposed relational feature transfer learning algorithm (RF-TL) embodies an extended structural equation modelling (SEM) as a method for constructing KGs. Additionally, in fields such as medicine, economics, and law related to people's lives and property safety and security, the knowledge of domain experts is a gold standard. This paper introduces the causal analysis and counterfactual inference in the TL domain that directs the transfer procedure. Different from traditional feature-based TL algorithms like transfer component analysis (TCA) and CORelation Alignment (CORAL), RF-TL not only considers relations between feature items but also utilizes causality knowledge, enabling it to perform well in practical cases. The algorithm was tested on two different healthcare-related datasets — sleep apnea questionnaire study data and COVID-19 case data on ICU admission — and compared its performance with TCA and CORAL. The experimental results show that RF-TL can generate better transferred models that give more accurate predictions with fewer input features.