Rethinking Robustness: A New Approach to Evaluating Feature Attribution Methods
Authors:
Preprint
Abstract
This paper studies the robustness of feature attribution methods for deep neural networks. It challenges the current notion of attributional robustness that largely ignores the difference in the model's outputs and introduces a new way of evaluating the robustness of attribution methods. Specifically, we propose a new definition of similar inputs, a new robustness metric, and a novel method based on generative adversarial networks to generate these inputs. In addition, we present a comprehensive evaluation with existing metrics and state-of-the-art attribution methods. Our findings highlight the need for a more objective metric that reveals the weaknesses of an attribution method rather than that of the neural network, thus providing a more accurate evaluation of the robustness of attribution methods.Keywords
All Related Versions
This publication has 4 references indexed in Scilit:
- LiteCovidNet: A lightweight deep neural network model for detection of COVID‐19 using X‐ray imagesInternational Journal of Imaging Systems and Technology, 2022
- CheXImageNet: a novel architecture for accurate classification of Covid-19 with chest x-ray digital images using deep convolutional neural networksHealth and Technology, 2022
- On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance PropagationPLOS ONE, 2015
- The MNIST Database of Handwritten Digit Images for Machine Learning Research [Best of the Web]IEEE Signal Processing Magazine, 2012