Shortcut Mitigation via Spurious-Positive Samples
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910216011907072 |
|---|---|
| author | Le, Phuong Quynh Schlötterer, Jörg Sadiya, Sari Roig, Gemma Seifert, Christin |
| author_facet | Le, Phuong Quynh Schlötterer, Jörg Sadiya, Sari Roig, Gemma Seifert, Christin |
| contents | Shortcut mitigation strategies commonly rely on training data annotations, group-balanced held-out data or the presence of all groups, i.e., all combinations of (spurious) attributes and classes, in the training data. However, these requirements are rarely met in practice. We instead propose a method for targeted model analysis to identify a small set of instances in which the model relies on spurious attributes. Using that set and following ``this feature should not be used for prediction'' reasoning, we identify highly relevant neurons in an intermediate layer and regularize their impact. This ensures that models learn to depend on informative features rather than being right for the wrong reasons, thereby improving robustness without requiring additional balanced held-out data or annotations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_13340 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Shortcut Mitigation via Spurious-Positive Samples Le, Phuong Quynh Schlötterer, Jörg Sadiya, Sari Roig, Gemma Seifert, Christin Machine Learning Shortcut mitigation strategies commonly rely on training data annotations, group-balanced held-out data or the presence of all groups, i.e., all combinations of (spurious) attributes and classes, in the training data. However, these requirements are rarely met in practice. We instead propose a method for targeted model analysis to identify a small set of instances in which the model relies on spurious attributes. Using that set and following ``this feature should not be used for prediction'' reasoning, we identify highly relevant neurons in an intermediate layer and regularize their impact. This ensures that models learn to depend on informative features rather than being right for the wrong reasons, thereby improving robustness without requiring additional balanced held-out data or annotations. |
| title | Shortcut Mitigation via Spurious-Positive Samples |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2605.13340 |