Enabling Regional Explainability by Automatic and Model-agnostic Rule Extraction
This work addresses the need for better explainability in fields like disease diagnosis and drug discovery, where data imbalance is common, but it is incremental as it builds on existing rule extraction methods.
The paper tackles the problem of rule extraction for explainable AI in imbalanced datasets, where existing methods compromise performance for minority classes, and proposes a model-agnostic approach that automatically generates rules for numerical features, enhancing regional explainability and reducing computational costs.
In Explainable AI, rule extraction translates model knowledge into logical rules, such as IF-THEN statements, crucial for understanding patterns learned by black-box models. This could significantly aid in fields like disease diagnosis, disease progression estimation, or drug discovery. However, such application domains often contain imbalanced data, with the class of interest underrepresented. Existing methods inevitably compromise the performance of rules for the minor class to maximise the overall performance. As the first attempt in this field, we propose a model-agnostic approach for extracting rules from specific subgroups of data, featuring automatic rule generation for numerical features. This method enhances the regional explainability of machine learning models and offers wider applicability compared to existing methods. We additionally introduce a new method for selecting features to compose rules, reducing computational costs in high-dimensional spaces. Experiments across various datasets and models demonstrate the effectiveness of our methods.