Computing Rule-Based Explanations by Leveraging Counterfactuals

TL;DR

This paper introduces a novel, efficient method for generating rule-based explanations for high-stakes machine learning decisions by leveraging the duality with counterfactual explanations, resulting in higher quality and comparable performance.

Contribution

The paper presents a duality theorem linking rule-based and counterfactual explanations, and develops an efficient algorithm that improves explanation quality without sacrificing performance.

Findings

The proposed method produces higher quality explanations than previous systems.

It achieves comparable or better computational performance.

Experiments validate the effectiveness of leveraging counterfactual explanations for rule-based explanations.

Abstract

Sophisticated machine models are increasingly used for high-stakes decisions in everyday life. There is an urgent need to develop effective explanation techniques for such automated decisions. Rule-Based Explanations have been proposed for high-stake decisions like loan applications, because they increase the users' trust in the decision. However, rule-based explanations are very inefficient to compute, and existing systems sacrifice their quality in order to achieve reasonable performance. We propose a novel approach to compute rule-based explanations, by using a different type of explanation, Counterfactual Explanations, for which several efficient systems have already been developed. We prove a Duality Theorem, showing that rule-based and counterfactual-based explanations are dual to each other, then use this observation to develop an efficient algorithm for computing rule-based explanations, which uses the counterfactual-based explanation as an oracle. We conduct extensive experiments showing that our system computes rule-based explanations of higher quality, and with the same or better performance, than two previous systems, MinSetCover and Anchor.