提出新算法FaVeX，让神经网络解释更快速可靠。
Faster Verified Explanations for Neural Networks
- 动态混合批处理与串行处理，复用查询信息加速计算
- 在含数十万非线性激活的模型上实现可验证解释
- 新定义的解释框架能反映验证器的不完整性，适合严谨场景
可验证解释为黑箱神经网络决策提供理论保障，但因需多次调用复杂度呈指数级增长的网络验证器而面临显著可扩展性挑战。本文提出FaVeX算法，通过动态结合输入特征的批量与串行处理，并复用先前查询中关于特征不变性证明及预测变化特征赋值搜索的信息，显著加速计算过程。此外，我们提出一种新型分层定义的可验证解释——验证器最优鲁棒解释，显式将验证器的不完备性纳入解释框架。全面实验表明，FaVeX与验证器最优鲁棒解释共同实现了优异的可扩展性，可在包含数十万非线性激活的神经网络上生成有意义的形式化解释。
原文摘要 · Abstract (English)
Verified explanations are a principled way to explain the decisions taken by neural networks, which are otherwise black-box in nature. However, these techniques face significant scalability challenges, as they require multiple calls to neural network verifiers, each of them with an exponential worst-case complexity. We present FaVeX, a novel algorithm to compute verified explanations. FaVeX accelerates the computation by dynamically combining batch and sequential processing of input features, and by reusing information from previous queries, both when proving invariances with respect to certain input features, and when searching for feature assignments altering the prediction. Furthermore, we present a novel and hierarchical definition of verified explanations, termed verifieroptimal robust explanations, that explicitly factors the incompleteness of network verifiers within the explanation. Our comprehensive experimental evaluation demonstrates the superior scalability of both FaVeX, and of verifier-optimal robust explanations, which together can produce meaningful formal explanation on networks with hundreds of thousands of non-linear activations.
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。