Pattern-Guided Integrated Gradients
This work addresses the need for more robust explainability methods in machine learning, though it appears incremental as it builds on existing techniques.
The authors tackled the challenge of improving neural network explainability by combining Integrated Gradients and PatternAttribution into Pattern-Guided Integrated Gradients (PGIG), which outperformed nine alternative methods in a large-scale image degradation experiment.
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.