Explaining Predictive Uncertainty by Exposing Second-Order Effects
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912121454854144 |
|---|---|
| author | Bley, Florian Lapuschkin, Sebastian Samek, Wojciech Montavon, Grégoire |
| author_facet | Bley, Florian Lapuschkin, Sebastian Samek, Wojciech Montavon, Grégoire |
| contents | Explainable AI has brought transparency into complex ML blackboxes, enabling, in particular, to identify which features these models use for their predictions. So far, the question of explaining predictive uncertainty, i.e. why a model 'doubts', has been scarcely studied. Our investigation reveals that predictive uncertainty is dominated by second-order effects, involving single features or product interactions between them. We contribute a new method for explaining predictive uncertainty based on these second-order effects. Computationally, our method reduces to a simple covariance computation over a collection of first-order explanations. Our method is generally applicable, allowing for turning common attribution techniques (LRP, Gradient x Input, etc.) into powerful second-order uncertainty explainers, which we call CovLRP, CovGI, etc. The accuracy of the explanations our method produces is demonstrated through systematic quantitative evaluations, and the overall usefulness of our method is demonstrated via two practical showcases. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_17441 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Explaining Predictive Uncertainty by Exposing Second-Order Effects Bley, Florian Lapuschkin, Sebastian Samek, Wojciech Montavon, Grégoire Machine Learning Artificial Intelligence Explainable AI has brought transparency into complex ML blackboxes, enabling, in particular, to identify which features these models use for their predictions. So far, the question of explaining predictive uncertainty, i.e. why a model 'doubts', has been scarcely studied. Our investigation reveals that predictive uncertainty is dominated by second-order effects, involving single features or product interactions between them. We contribute a new method for explaining predictive uncertainty based on these second-order effects. Computationally, our method reduces to a simple covariance computation over a collection of first-order explanations. Our method is generally applicable, allowing for turning common attribution techniques (LRP, Gradient x Input, etc.) into powerful second-order uncertainty explainers, which we call CovLRP, CovGI, etc. The accuracy of the explanations our method produces is demonstrated through systematic quantitative evaluations, and the overall usefulness of our method is demonstrated via two practical showcases. |
| title | Explaining Predictive Uncertainty by Exposing Second-Order Effects |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2401.17441 |