Towards Aligned Data Removal via Twin Machine Unlearning
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_ | 1866908344995807232 |
|---|---|
| author | Ji, Haoxuan Lin, Zheng Sun, Yuyao Fei, Gao Wang, Yuhang Gao, Haichang Niu, Zhenxing |
| author_facet | Ji, Haoxuan Lin, Zheng Sun, Yuyao Fei, Gao Wang, Yuhang Gao, Haichang Niu, Zhenxing |
| contents | Modern privacy regulations have spurred the evolution of machine unlearning, a technique that enables the removal of data from an already trained ML model without requiring retraining from scratch. Previous unlearning methods tend to induce the model to achieve lowest classification accuracy on the removal data. Nonetheless, the authentic objective of machine unlearning is to align the unlearned model with the gold model, i.e., achieving the same classification accuracy as the gold model. For this purpose, we present a Twin Machine Unlearning (TMU) approach, where a twin unlearning problem is defined corresponding to the original unlearning problem. As a results, the generalization-label predictor trained on the twin problem can be transferred to the original problem, facilitating aligned data removal. Comprehensive empirical experiments illustrate that our approach significantly enhances the alignment between the unlearned model and the gold model. Meanwhile, our method allows data removal without compromising the model accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_11433 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Aligned Data Removal via Twin Machine Unlearning Ji, Haoxuan Lin, Zheng Sun, Yuyao Fei, Gao Wang, Yuhang Gao, Haichang Niu, Zhenxing Machine Learning Artificial Intelligence Modern privacy regulations have spurred the evolution of machine unlearning, a technique that enables the removal of data from an already trained ML model without requiring retraining from scratch. Previous unlearning methods tend to induce the model to achieve lowest classification accuracy on the removal data. Nonetheless, the authentic objective of machine unlearning is to align the unlearned model with the gold model, i.e., achieving the same classification accuracy as the gold model. For this purpose, we present a Twin Machine Unlearning (TMU) approach, where a twin unlearning problem is defined corresponding to the original unlearning problem. As a results, the generalization-label predictor trained on the twin problem can be transferred to the original problem, facilitating aligned data removal. Comprehensive empirical experiments illustrate that our approach significantly enhances the alignment between the unlearned model and the gold model. Meanwhile, our method allows data removal without compromising the model accuracy. |
| title | Towards Aligned Data Removal via Twin Machine Unlearning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2408.11433 |