Generalizing Logic-based Explanations for Machine Learning Classifiers via Optimization

TL;DR

This paper introduces two new methods, Onestep and Twostep, for generating logic-based explanations of machine learning classifiers, with Twostep significantly improving explanation coverage while maintaining correctness.

Contribution

The paper presents a novel single-step explanation method and an incremental approach that enhances coverage compared to existing logic-based explanation techniques.

Findings

Twostep increases explanation coverage by up to 72.60% on average.

Onestep reduces explanation generation time by eliminating iterative steps.

Both methods maintain correctness guarantees in explanations.

Abstract

Machine learning models support decision-making, yet the reasons behind their predictions are opaque. Clear and reliable explanations help users make informed decisions and avoid blindly trusting model outputs. However, many existing explanation methods fail to guarantee correctness. Logic-based approaches ensure correctness but often offer overly constrained explanations, limiting coverage. Recent work addresses this by incrementally expanding explanations while maintaining correctness. This process is performed separately for each feature, adjusting both its upper and lower bounds. However, this approach faces a trade-off: smaller increments incur high computational costs, whereas larger ones may lead to explanations covering fewer instances. To overcome this, we propose two novel methods. Onestep builds upon this prior work, generating explanations in a single step for each feature and each bound, eliminating the overhead of an iterative process. \textit{Twostep} takes a gradual approach, improving coverage. Experimental results show that Twostep significantly increases explanation coverage (by up to 72.60\% on average across datasets) compared to Onestep and, consequently, to prior work.