通过结合边界传播与约束简化，显著提升神经网络逻辑解释的效率。
Bound Propagation meets Constraint Simplification: Improving Logic-based XAI for Neural Networks
- 利用边界传播生成紧致约束，减少冗余变量
- 实验显示解释时间最高降低89.26%
- 特别适合大型神经网络的可解释性分析
基于逻辑的神经网络解释方法能提供形式化正确性保证和无冗余性，但通常计算开销大，尤其在大型网络上。本文通过将边界传播与约束简化相结合，改进了这类方法的效率。这些简化基于传播结果，能紧缩神经元边界并消除不必要的二值变量，从而加速解释过程。实验表明，该方法在较大网络上可使解释时间最多减少89.26%。
原文摘要 · Abstract (English)
Logic-based methods for explaining neural network decisions offer formal guarantees of correctness and non-redundancy, but they often suffer from high computational costs, especially for large networks. In this work, we improve the efficiency of such methods by combining bound propagation with constraint simplification. These simplifications, derived from the propagation, tighten neuron bounds and eliminate unnecessary binary variables, making the explanation process more efficient. Our experiments suggest that combining these techniques reduces explanation time by up to 89.26\%, particularly for larger neural networks.
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。