Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.07026 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913831922434048 |
|---|---|
| author | Egger, Maximilian Bitar, Rawad Urbanke, Rüdiger |
| author_facet | Egger, Maximilian Bitar, Rawad Urbanke, Rüdiger |
| contents | Machine unlearning is essential for meeting legal obligations such as the right to be forgotten, which requires the removal of specific data from machine learning models upon request. While several approaches to unlearning have been proposed, existing solutions often struggle with efficiency and, more critically, with the verification of unlearning - particularly in the case of weak unlearning guarantees, where verification remains an open challenge. We introduce a generalized variant of the standard unlearning metric that enables more efficient and precise unlearning strategies. We also present an unlearning-aware training procedure that, in many cases, allows for exact unlearning. We term our approach MaxRR. When exact unlearning is not feasible, MaxRR still supports efficient unlearning with properties closely matching those achieved through full retraining. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_07026 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Efficient Machine Unlearning by Model Splitting and Core Sample Selection Egger, Maximilian Bitar, Rawad Urbanke, Rüdiger Machine Learning Machine unlearning is essential for meeting legal obligations such as the right to be forgotten, which requires the removal of specific data from machine learning models upon request. While several approaches to unlearning have been proposed, existing solutions often struggle with efficiency and, more critically, with the verification of unlearning - particularly in the case of weak unlearning guarantees, where verification remains an open challenge. We introduce a generalized variant of the standard unlearning metric that enables more efficient and precise unlearning strategies. We also present an unlearning-aware training procedure that, in many cases, allows for exact unlearning. We term our approach MaxRR. When exact unlearning is not feasible, MaxRR still supports efficient unlearning with properties closely matching those achieved through full retraining. |
| title | Efficient Machine Unlearning by Model Splitting and Core Sample Selection |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2505.07026 |