Back to Search
Start Over
Unlearning with Fisher Masking
- Publication Year :
- 2023
-
Abstract
- Machine unlearning aims to revoke some training data after learning in response to requests from users, model developers, and administrators. Most previous methods are based on direct fine-tuning, which may neither remove data completely nor retain full performances on the remain data. In this work, we find that, by first masking some important parameters before fine-tuning, the performances of unlearning could be significantly improved. We propose a new masking strategy tailored to unlearning based on Fisher information. Experiments on various datasets and network structures show the effectiveness of the method: without any fine-tuning, the proposed Fisher masking could unlearn almost completely while maintaining most of the performance on the remain data. It also exhibits stronger stability compared to other unlearning baselines
- Subjects :
- Computer Science - Machine Learning
Subjects
Details
- Database :
- arXiv
- Publication Type :
- Report
- Accession number :
- edsarx.2310.05331
- Document Type :
- Working Paper