Toward Efficient Data-Free 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_ | 1866917872377266176 |
|---|---|
| author | Zhang, Chenhao Shen, Shaofei Chen, Weitong Xu, Miao |
| author_facet | Zhang, Chenhao Shen, Shaofei Chen, Weitong Xu, Miao |
| contents | Machine unlearning without access to real data distribution is challenging. The existing method based on data-free distillation achieved unlearning by filtering out synthetic samples containing forgetting information but struggled to distill the retaining-related knowledge efficiently. In this work, we analyze that such a problem is due to over-filtering, which reduces the synthesized retaining-related information. We propose a novel method, Inhibited Synthetic PostFilter (ISPF), to tackle this challenge from two perspectives: First, the Inhibited Synthetic, by reducing the synthesized forgetting information; Second, the PostFilter, by fully utilizing the retaining-related information in synthesized samples. Experimental results demonstrate that the proposed ISPF effectively tackles the challenge and outperforms existing methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_13790 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Toward Efficient Data-Free Unlearning Zhang, Chenhao Shen, Shaofei Chen, Weitong Xu, Miao Machine Learning Machine unlearning without access to real data distribution is challenging. The existing method based on data-free distillation achieved unlearning by filtering out synthetic samples containing forgetting information but struggled to distill the retaining-related knowledge efficiently. In this work, we analyze that such a problem is due to over-filtering, which reduces the synthesized retaining-related information. We propose a novel method, Inhibited Synthetic PostFilter (ISPF), to tackle this challenge from two perspectives: First, the Inhibited Synthetic, by reducing the synthesized forgetting information; Second, the PostFilter, by fully utilizing the retaining-related information in synthesized samples. Experimental results demonstrate that the proposed ISPF effectively tackles the challenge and outperforms existing methods. |
| title | Toward Efficient Data-Free Unlearning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2412.13790 |