Slice and Explain: Logic-Based Explanations for Neural Networks through Domain Slicing

TL;DR

This paper introduces a domain slicing technique to improve the efficiency of logic-based explanations for neural networks, reducing explanation time by up to 40% and enhancing interpretability.

Contribution

The paper presents a novel domain slicing method that simplifies logical constraints, making explanations for neural networks more scalable and efficient.

Findings

Explanation time reduced by up to 40%

Domain slicing improves scalability of logic-based explanations

Enhanced interpretability of neural network predictions

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.