Conceptualizing Uncertainty: A Concept-based Approach to Explaining Uncertainty
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912506433241088 |
|---|---|
| author | Roberts, Isaac Schulz, Alexander Schroeder, Sarah Hinder, Fabian Hammer, Barbara |
| author_facet | Roberts, Isaac Schulz, Alexander Schroeder, Sarah Hinder, Fabian Hammer, Barbara |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_03443 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Conceptualizing Uncertainty: A Concept-based Approach to Explaining Uncertainty Roberts, Isaac Schulz, Alexander Schroeder, Sarah Hinder, Fabian Hammer, Barbara Machine Learning Artificial Intelligence 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. |
| title | Conceptualizing Uncertainty: A Concept-based Approach to Explaining Uncertainty |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2503.03443 |