CORTEX: A Cost-Sensitive Rule and Tree Extraction Method

TL;DR

The paper addresses the need for interpretable explanations of black-box predictors in multi-class, imbalanced settings by introducing CORTEX, a cost-sensitive rule and tree extraction method. CORTEX extends the cost-sensitive decision tree (CSDT) with an $n$-dimensional class-dependent cost matrix and converts the resulting tree into IF-THEN rules using cost-sensitive probabilities $p_{mk}$ defined by $p_{mk} = \frac{1 - avgcost_m(f(k))}{\sum_{i=1}^K avgcost_m(f(i))}$, where $avgcost_m(f(i)) = \frac{cost(f(i))}{\sum_{i=1}^K cost(f(i))}$, and a default matrix $C_{ij} = \frac{N_i + N_j}{N_i}$. The method is evaluated on eight UCI datasets with two neural-network backbones, comparing against six baseline rule-extractors and a weighted DT, using six explainability metrics. Results show CORTEX achieves complete coverage with smaller, shorter rule sets and competitive fidelity and correctness, demonstrating a strong balance between interpretability and predictive alignment, particularly for datasets with many classes and skewed class distributions. The findings support CORTEX as a scalable, post-hoc XAI tool for generating clear, human-understandable rules while retaining good predictive performance.

Abstract

Tree-based and rule-based machine learning models play pivotal roles in explainable artificial intelligence (XAI) due to their unique ability to provide explanations in the form of tree or rule sets that are easily understandable and interpretable, making them essential for applications in which trust in model decisions is necessary. These transparent models are typically used in surrogate modeling, a post-hoc XAI approach for explaining the logic of black-box models, enabling users to comprehend and trust complex predictive systems while maintaining competitive performance. This study proposes the Cost-Sensitive Rule and Tree Extraction (CORTEX) method, a novel rule-based XAI algorithm grounded in the multi-class cost-sensitive decision tree (CSDT) method. The original version of the CSDT is extended to classification problems with more than two classes by inducing the concept of an n-dimensional class-dependent cost matrix. The performance of CORTEX as a rule-extractor XAI method is compared to other post-hoc tree and rule extraction methods across several datasets with different numbers of classes. Several quantitative evaluation metrics are employed to assess the explainability of generated rule sets. Our findings demonstrate that CORTEX is competitive with other tree-based methods and can be superior to other rule-based methods across different datasets. The extracted rule sets suggest the advantages of using the CORTEX method over other methods by producing smaller rule sets with shorter rules on average across datasets with a diverse number of classes. Overall, the results underscore the potential of CORTEX as a powerful XAI tool for scenarios that require the generation of clear, human-understandable rules while maintaining good predictive performance.

Figures (12)

• Figure 1: Experimental study design for creating and evaluating XAI surrogate models using six rule extractors.
• Figure 2: Distribution of six quantitative metrics for evaluating rule-extractor XAI methods across several datasets.
• Figure 3: Normalized ranks for six rule extraction XAI methods across datasets.
• Figure 4: Distribution of six quantitative metrics for evaluating rule-extractor XAI methods for abalone dataset.
• Figure 5: Distribution of six quantitative metrics for evaluating rule-extractor XAI methods for the contraceptive dataset.