Improving Compactness and Reducing Ambiguity of CFIRE Rule-Based Explanations

TL;DR

This paper enhances CFIRE, a rule-based explanation method for tabular data models, by reducing ambiguity and increasing compactness through a post-hoc pruning strategy, maintaining accuracy while improving interpretability.

Contribution

It introduces a novel pruning approach that refines CFIRE explanations, making them more concise and less ambiguous without sacrificing fidelity.

Findings

Reduced rule ambiguity in CFIRE explanations.

Smaller, more interpretable rule models.

Minimal impact on model fidelity.

Abstract

Models trained on tabular data are widely used in sensitive domains, increasing the demand for explanation methods to meet transparency needs. CFIRE is a recent algorithm in this domain that constructs compact surrogate rule models from local explanations. While effective, CFIRE may assign rules associated with different classes to the same sample, introducing ambiguity. We investigate this ambiguity and propose a post-hoc pruning strategy that removes rules with low contribution or conflicting coverage, yielding smaller and less ambiguous models while preserving fidelity. Experiments across multiple datasets confirm these improvements with minimal impact on predictive performance.