Uncertainty Quantification for Gradient-based Explanations in Neural Networks

arXiv:2403.17224v1 Announce Type: new
Abstract: Explanation methods help understand the reasons for a model's prediction. These methods are increasingly involved in model debugging, performance optimization, and gaining insights into the workings of a model. With such critical applications of these methods, it is imperative to measure the uncertainty associated with the explanations generated by these methods. In this paper, we propose a pipeline to ascertain the explanation uncertainty of neural networks by combining uncertainty estimation methods and explanation methods. We …

abstract applications arxiv cs.ai cs.lg debugging gradient insights networks neural networks optimization performance prediction quantification type uncertainty