Conceptualizing Uncertainty: A Concept-based Approach to Explaining Uncertainty

Abstract

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 settings, remain an open challenge. Existing work focuses on feature attribution approaches which are restricted to local explanations. Understanding uncertainty, its origins, and characteristics on a global scale is crucial for enhancing interpretability and trust in a model's predictions. In this work, we propose to explain the uncertainty in high-dimensional data classification settings by means of concept activation vectors which give rise to local and global explanations of uncertainty. We demonstrate the utility of the generated explanations by leveraging them to refine and improve our model.

References in corpus (6)

• Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods
• A Survey on the Explainability of Supervised Machine Learning
• Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting
• From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation
• DeepView: Visualizing Classification Boundaries of Deep Neural Networks as Scatter Plots Using Discriminative Dimensionality Reduction
• Explaining Predictive Uncertainty by Exposing Second-Order Effects