Uncertainty Quantification for Gradient-based Explanations in Neural Networks
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912327340654592 |
|---|---|
| author | Mulye, Mihir Valdenegro-Toro, Matias |
| author_facet | Mulye, Mihir Valdenegro-Toro, Matias |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_17224 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Uncertainty Quantification for Gradient-based Explanations in Neural Networks Mulye, Mihir Valdenegro-Toro, Matias Machine Learning Artificial Intelligence 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. |
| title | Uncertainty Quantification for Gradient-based Explanations in Neural Networks |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2403.17224 |