Pattern-Guided Integrated Gradients

Abstract

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.

arXiv commentPresented at the ICML 2020 Workshop on Human Interpretability in Machine Learning (WHI)

References in corpus (9)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Axiomatic Attribution for Deep Networks
• Striving for Simplicity: The All Convolutional Net
• SmoothGrad: removing noise by adding noise
• Sanity Checks for Saliency Maps
• Not Just a Black Box: Learning Important Features Through Propagating Activation Differences
• A Benchmark for Interpretability Methods in Deep Neural Networks
• Learning how to explain neural networks: PatternNet and PatternAttribution
• Understanding Integrated Gradients with SmoothTaylor for Deep Neural Network Attribution