Generalizing Logic-based Explanations for Machine Learning Classifiers via Optimization

📅 2026-03-02
📈 Citations: 0
Influential: 0
📄 PDF

career value

173K/year
🤖 AI Summary
Existing methods for logical explanations often struggle to simultaneously ensure correctness and achieve broad coverage. To address this challenge, this work proposes two novel approaches—Onestep and Twostep—that generate high-coverage logical-form explanations while strictly preserving correctness. Onestep employs a single-step optimization framework, whereas Twostep adopts a progressive strategy that iteratively refines explanations. Both methods integrate logical rule generation, boundary optimization, feature bound adjustment, and coverage maximization techniques. Experimental results demonstrate that Twostep significantly outperforms current state-of-the-art methods, improving average explanation coverage by 72.60% across multiple datasets.

Technology Category

Application Category

📝 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.
Problem

Research questions and friction points this paper is trying to address.

logic-based explanations
explanation coverage
machine learning interpretability
correctness
feature bounds
Innovation

Methods, ideas, or system contributions that make the work stand out.

logic-based explanations
explanation coverage
correctness guarantee
optimization
machine learning interpretability
🔎 Similar Papers
2024-07-30Conference on Empirical Methods in Natural Language ProcessingCitations: 0
F
Francisco Mateus Rocha Filho
Instituto Federal de Educação, Ciência e Tecnologia do Ceará (IFCE), Fortaleza, Brazil
A
Ajalmar Rê go da Rocha Neto
Instituto Federal de Educação, Ciência e Tecnologia do Ceará (IFCE), Fortaleza, Brazil
T
Thiago Alves Rocha
Instituto Federal de Educação, Ciência e Tecnologia do Ceará (IFCE), Fortaleza, Brazil