paper-with-me

홈 › Papers

Uncertainty Quantification for Gradient-based Explanations in Neural Networks

2024-03-25 · Mihir Mulye, Matias Valdenegro-Toro

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.

📄 PDF Abstract BibTeX arXiv:2403.17224

Code (0)

등록된 구현이 없습니다.

Tasks

Uncertainty Quantification

Similar Papers 제목 키워드 기반

QUCE: The Minimisation and Quantification of Path-Based Uncertainty for Generative Counterfactual Explanations

2024-02-27 · Jamie Duell, Monika Seisenberger, Hsuan Fu, Xiuyi Fan

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 Models

Fast Calibrated Explanations: Efficient and Uncertainty-Aware Explanations for Machine Learning Models

2024-10-28 · Tuwe Löfström, Fatima Rabia Yapicioglu, Alessandra Stramiglio, Helena Löfström 외

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 Quantification

VOICE: Variance of Induced Contrastive Explanations to quantify Uncertainty in Neural Network Interpretability

2024-06-01 · Mohit Prabhushankar, Ghassan AlRegib

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 Visualization

Calibrated Explanations: with Uncertainty Information and Counterfactuals

2023-05-03 · Helena Lofstrom, Tuwe Lofstrom, Ulf Johansson, Cecilia Sonstrod

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+1

Conceptualizing Uncertainty

2025-03-05 · Isaac Roberts, Alexander Schulz, Sarah Schroeder, Fabian Hinder 외

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