Slice and Explain: Logic-Based Explanations for Neural Networks through Domain Slicing
Logic in Computer Science
2026-02-26 v1 Machine Learning
Abstract
Neural networks (NNs) are pervasive across various domains but often lack interpretability. To address the growing need for explanations, logic-based approaches have been proposed to explain predictions made by NNs, offering correctness guarantees. However, scalability remains a concern in these methods. This paper proposes an approach leveraging domain slicing to facilitate explanation generation for NNs. By reducing the complexity of logical constraints through slicing, we decrease explanation time by up to 40\% less time, as indicated through comparative experiments. Our findings highlight the efficacy of domain slicing in enhancing explanation efficiency for NNs.
Cite
@article{arxiv.2602.22115,
title = {Slice and Explain: Logic-Based Explanations for Neural Networks through Domain Slicing},
author = {Luiz Fernando Paulino Queiroz and Carlos Henrique Leitão Cavalcante and Thiago Alves Rocha},
journal= {arXiv preprint arXiv:2602.22115},
year = {2026}
}
Comments
Preprint version. For the final published version, see the DOI below