论文标题
模式引导的集成梯度
Pattern-Guided Integrated Gradients
论文作者
论文摘要
综合梯度（IG）和模式贡献（PA）是神经网络的两种已建立的解释性方法。这两种方法在理论上都是有充分根据的。但是，它们旨在克服不同的挑战。在这项工作中，我们将这两种方法组合为一种新方法，即模式引导的集成梯度（PGIG）。 PGIG从父母方法中继承了重要的属性，并通过原始作品失败的压力测试。此外，我们在大规模的图像降解实验中对九种替代性解释性方法（包括其母体方法）进行了基准测试，并发现其表现优于所有这些方法。
Integrated Gradients (IG) and PatternAttribution (PA) are two established explainability methods for neural networks. Both methods are theoretically well-founded. However, they were designed to overcome different challenges. In this work, we combine the two methods into a new method, Pattern-Guided Integrated Gradients (PGIG). PGIG inherits important properties from both parent methods and passes stress tests that the originals fail. In addition, we benchmark PGIG against nine alternative explainability approaches (including its parent methods) in a large-scale image degradation experiment and find that it outperforms all of them.
