Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.13711 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918249540616192 |
|---|---|
| author | Goel, Aadya Sridhar, Mayuri |
| author_facet | Goel, Aadya Sridhar, Mayuri |
| contents | Machine unlearning aims to efficiently remove the influence of specific training data from a model without full retraining. While much progress has been made in unlearning for LLMs, document classification models remain relatively understudied. In this paper, we study class-level unlearning for document classifiers and present Hessian Reassignment, a two-step, model-agnostic solution. First, we perform a single influence-style update that subtracts the contribution of all training points from the target class by solving a Hessian-vector system with conjugate gradients, requiring only gradient and Hessian-vector products. Second, in contrast to common unlearning baselines that randomly reclassify deleted-class samples, we enforce a decision-space guarantee via Top-1 classification. On standard text benchmarks, Hessian Reassignment achieves retained-class accuracy close to full retrain-without-class while running orders of magnitude faster. Additionally, it consistently lowers membership-inference advantage on the removed class, measured with pooled multi-shadow attacks. These results demonstrate a practical, principled path to efficient class unlearning in document classification. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_13711 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Delete and Retain: Efficient Unlearning for Document Classification Goel, Aadya Sridhar, Mayuri Machine Learning Machine unlearning aims to efficiently remove the influence of specific training data from a model without full retraining. While much progress has been made in unlearning for LLMs, document classification models remain relatively understudied. In this paper, we study class-level unlearning for document classifiers and present Hessian Reassignment, a two-step, model-agnostic solution. First, we perform a single influence-style update that subtracts the contribution of all training points from the target class by solving a Hessian-vector system with conjugate gradients, requiring only gradient and Hessian-vector products. Second, in contrast to common unlearning baselines that randomly reclassify deleted-class samples, we enforce a decision-space guarantee via Top-1 classification. On standard text benchmarks, Hessian Reassignment achieves retained-class accuracy close to full retrain-without-class while running orders of magnitude faster. Additionally, it consistently lowers membership-inference advantage on the removed class, measured with pooled multi-shadow attacks. These results demonstrate a practical, principled path to efficient class unlearning in document classification. |
| title | Delete and Retain: Efficient Unlearning for Document Classification |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2512.13711 |