Challenges in interpretability of additive models
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912326071877632 |
|---|---|
| author | Zhang, Xinyu Martinelli, Julien John, ST |
| author_facet | Zhang, Xinyu Martinelli, Julien John, ST |
| contents | We review generalized additive models as a type of ``transparent'' model that has recently seen renewed interest in the deep learning community as neural additive models. We highlight multiple types of nonidentifiability in this model class and discuss challenges in interpretability, arguing for restraint when claiming ``interpretability'' or ``suitability for safety-critical applications'' of such models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_10169 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Challenges in interpretability of additive models Zhang, Xinyu Martinelli, Julien John, ST Machine Learning We review generalized additive models as a type of ``transparent'' model that has recently seen renewed interest in the deep learning community as neural additive models. We highlight multiple types of nonidentifiability in this model class and discuss challenges in interpretability, arguing for restraint when claiming ``interpretability'' or ``suitability for safety-critical applications'' of such models. |
| title | Challenges in interpretability of additive models |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2504.10169 |