Revisiting the robustness of post-hoc interpretability methods
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_ | 1866917736220721152 |
|---|---|
| author | Wei, Jiawen Turbé, Hugues Mengaldo, Gianmarco |
| author_facet | Wei, Jiawen Turbé, Hugues Mengaldo, Gianmarco |
| contents | Post-hoc interpretability methods play a critical role in explainable artificial intelligence (XAI), as they pinpoint portions of data that a trained deep learning model deemed important to make a decision. However, different post-hoc interpretability methods often provide different results, casting doubts on their accuracy. For this reason, several evaluation strategies have been proposed to understand the accuracy of post-hoc interpretability. Many of these evaluation strategies provide a coarse-grained assessment -- i.e., they evaluate how the performance of the model degrades on average by corrupting different data points across multiple samples. While these strategies are effective in selecting the post-hoc interpretability method that is most reliable on average, they fail to provide a sample-level, also referred to as fine-grained, assessment. In other words, they do not measure the robustness of post-hoc interpretability methods. We propose an approach and two new metrics to provide a fine-grained assessment of post-hoc interpretability methods. We show that the robustness is generally linked to its coarse-grained performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_19683 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Revisiting the robustness of post-hoc interpretability methods Wei, Jiawen Turbé, Hugues Mengaldo, Gianmarco Machine Learning Artificial Intelligence Post-hoc interpretability methods play a critical role in explainable artificial intelligence (XAI), as they pinpoint portions of data that a trained deep learning model deemed important to make a decision. However, different post-hoc interpretability methods often provide different results, casting doubts on their accuracy. For this reason, several evaluation strategies have been proposed to understand the accuracy of post-hoc interpretability. Many of these evaluation strategies provide a coarse-grained assessment -- i.e., they evaluate how the performance of the model degrades on average by corrupting different data points across multiple samples. While these strategies are effective in selecting the post-hoc interpretability method that is most reliable on average, they fail to provide a sample-level, also referred to as fine-grained, assessment. In other words, they do not measure the robustness of post-hoc interpretability methods. We propose an approach and two new metrics to provide a fine-grained assessment of post-hoc interpretability methods. We show that the robustness is generally linked to its coarse-grained performance. |
| title | Revisiting the robustness of post-hoc interpretability methods |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2407.19683 |