Explaining Predictions by Characteristic Rules

TL;DR

This paper introduces CEGA, a novel explanation method that uses characteristic rules to improve interpretability and fidelity of local explanations, outperforming existing methods in trade-offs between complexity and accuracy.

Contribution

The paper proposes CEGA, a new technique that aggregates local explanations into characteristic rules, enhancing interpretability and fidelity over state-of-the-art methods.

Findings

CEGA provides a better trade-off between fidelity and complexity.

CEGA and Anchors outperform GLocalX in fidelity.

Using CEGA with SHAP or Anchors yields higher fidelity than with LIME.

Abstract

Characteristic rules have been advocated for their ability to improve interpretability over discriminative rules within the area of rule learning. However, the former type of rule has not yet been used by techniques for explaining predictions. A novel explanation technique, called CEGA (Characteristic Explanatory General Association rules), is proposed, which employs association rule mining to aggregate multiple explanations generated by any standard local explanation technique into a set of characteristic rules. An empirical investigation is presented, in which CEGA is compared to two state-of-the-art methods, Anchors and GLocalX, for producing local and aggregated explanations in the form of discriminative rules. The results suggest that the proposed approach provides a better trade-off between fidelity and complexity compared to the two state-of-the-art approaches; CEGA and Anchors significantly outperform GLocalX with respect to fidelity, while CEGA and GLocalX significantly outperform Anchors with respect to the number of generated rules. The effect of changing the format of the explanations of CEGA to discriminative rules and using LIME and SHAP as local explanation techniques instead of Anchors are also investigated. The results show that the characteristic explanatory rules still compete favorably with rules in the standard discriminative format. The results also indicate that using CEGA in combination with either SHAP or Anchors consistently leads to a higher fidelity compared to using LIME as the local explanation technique.