Slice and Explain: Logic-Based Explanations for Neural Networks through Domain Slicing
This work addresses the need for more efficient interpretability methods in AI, though it is incremental as it builds on existing logic-based approaches.
The paper tackled the scalability problem in logic-based explanations for neural networks by using domain slicing to reduce logical constraint complexity, resulting in up to 40% faster explanation generation.
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.