Constructing sensible baselines for Integrated Gradients
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_ | 1866916530786140160 |
|---|---|
| author | Bardhan, Jai Neeraj, Cyrin Rawat, Mihir Mitra, Subhadip |
| author_facet | Bardhan, Jai Neeraj, Cyrin Rawat, Mihir Mitra, Subhadip |
| contents | Machine learning methods have seen a meteoric rise in their applications in the scientific community. However, little effort has been put into understanding these "black box" models. We show how one can apply integrated gradients (IGs) to understand these models by designing different baselines, by taking an example case study in particle physics. We find that the zero-vector baseline does not provide good feature attributions and that an averaged baseline sampled from the background events provides consistently more reasonable attributions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_13864 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Constructing sensible baselines for Integrated Gradients Bardhan, Jai Neeraj, Cyrin Rawat, Mihir Mitra, Subhadip Machine Learning High Energy Physics - Experiment Machine learning methods have seen a meteoric rise in their applications in the scientific community. However, little effort has been put into understanding these "black box" models. We show how one can apply integrated gradients (IGs) to understand these models by designing different baselines, by taking an example case study in particle physics. We find that the zero-vector baseline does not provide good feature attributions and that an averaged baseline sampled from the background events provides consistently more reasonable attributions. |
| title | Constructing sensible baselines for Integrated Gradients |
| topic | Machine Learning High Energy Physics - Experiment |
| url | https://arxiv.org/abs/2412.13864 |