Uncertainty Quantification for Gradient-based Explanations in Neural Networks
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 use this pipeline to produce explanation distributions for the CIFAR-10, FER+, and California Housing datasets. By computing the coefficient of variation of these distributions, we evaluate the confidence in the explanation and determine that the explanations generated using Guided Backpropagation have low uncertainty associated with them. Additionally, we compute modified pixel insertion/deletion metrics to evaluate the quality of the generated explanations.
Code (0)
등록된 구현이 없습니다.
Tasks
Uncertainty QuantificationSimilar Papers 제목 키워드 기반
QUCE: The Minimisation and Quantification of Path-Based Uncertainty for Generative Counterfactual Explanations
Deep Neural Networks (DNNs) stand out as one of the most prominent approaches within the Machine Learning (ML) domain. The efficacy of DNNs has surged alongside recent increases in computational capacity, allowing these …
counterfactualExplainable ModelsFast Calibrated Explanations: Efficient and Uncertainty-Aware Explanations for Machine Learning Models
This paper introduces Fast Calibrated Explanations, a method designed for generating rapid, uncertainty-aware explanations for machine learning models. By incorporating perturbation techniques from ConformaSight - a glob…
Computational EfficiencyFeature ImportanceregressionUncertainty QuantificationVOICE: Variance of Induced Contrastive Explanations to quantify Uncertainty in Neural Network Interpretability
In this paper, we visualize and quantify the predictive uncertainty of gradient-based post hoc visual explanations for neural networks. Predictive uncertainty refers to the variability in the network predictions under pe…
Uncertainty VisualizationCalibrated Explanations: with Uncertainty Information and Counterfactuals
While local explanations for AI models can offer insights into individual predictions, such as feature importance, they are plagued by issues like instability. The unreliability of feature weights, often skewed due to po…
counterfactualExplainable artificial intelligenceExplainable Artificial Intelligence (XAI)Feature Importance+1Conceptualizing Uncertainty
Uncertainty in machine learning refers to the degree of confidence or lack thereof in a model's predictions. While uncertainty quantification methods exist, explanations of uncertainty, especially in high-dimensional set…
Uncertainty Quantification