用领域切片提升神经网络解释效率，提速最高达40%
Slice and Explain: Logic-Based Explanations for Neural Networks through Domain Slicing
- 通过领域切片降低逻辑约束复杂度
- 解释生成时间最多减少40%
- 适合需要快速可解释性的模型部署场景
神经网络在多个领域广泛应用，但可解释性不足。为满足解释需求，基于逻辑的方法虽能提供正确性保障，但存在可扩展性问题。本文提出利用领域切片来提升神经网络解释生成效率。通过切片降低逻辑约束的复杂度，实验表明解释时间最多减少40%。结果表明，领域切片能有效提升神经网络解释的效率。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。