FaLW: A Forgetting-aware Loss Reweighting for Long-tailed Unlearning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911460963123200 |
|---|---|
| author | Yu, Liheng Zhao, Zhe Wang, Yuxuan Wang, Pengkun Cao, Xiaofeng Wang, Binwu Wang, Yang |
| author_facet | Yu, Liheng Zhao, Zhe Wang, Yuxuan Wang, Pengkun Cao, Xiaofeng Wang, Binwu Wang, Yang |
| contents | Machine unlearning, which aims to efficiently remove the influence of specific data from trained models, is crucial for upholding data privacy regulations like the ``right to be forgotten". However, existing research predominantly evaluates unlearning methods on relatively balanced forget sets. This overlooks a common real-world scenario where data to be forgotten, such as a user's activity records, follows a long-tailed distribution. Our work is the first to investigate this critical research gap. We find that in such long-tailed settings, existing methods suffer from two key issues: \textit{Heterogeneous Unlearning Deviation} and \textit{Skewed Unlearning Deviation}. To address these challenges, we propose FaLW, a plug-and-play, instance-wise dynamic loss reweighting method. FaLW innovatively assesses the unlearning state of each sample by comparing its predictive probability to the distribution of unseen data from the same class. Based on this, it uses a forgetting-aware reweighting scheme, modulated by a balancing factor, to adaptively adjust the unlearning intensity for each sample. Extensive experiments demonstrate that FaLW achieves superior performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_18650 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FaLW: A Forgetting-aware Loss Reweighting for Long-tailed Unlearning Yu, Liheng Zhao, Zhe Wang, Yuxuan Wang, Pengkun Cao, Xiaofeng Wang, Binwu Wang, Yang Machine Learning Artificial Intelligence Machine unlearning, which aims to efficiently remove the influence of specific data from trained models, is crucial for upholding data privacy regulations like the ``right to be forgotten". However, existing research predominantly evaluates unlearning methods on relatively balanced forget sets. This overlooks a common real-world scenario where data to be forgotten, such as a user's activity records, follows a long-tailed distribution. Our work is the first to investigate this critical research gap. We find that in such long-tailed settings, existing methods suffer from two key issues: \textit{Heterogeneous Unlearning Deviation} and \textit{Skewed Unlearning Deviation}. To address these challenges, we propose FaLW, a plug-and-play, instance-wise dynamic loss reweighting method. FaLW innovatively assesses the unlearning state of each sample by comparing its predictive probability to the distribution of unseen data from the same class. Based on this, it uses a forgetting-aware reweighting scheme, modulated by a balancing factor, to adaptively adjust the unlearning intensity for each sample. Extensive experiments demonstrate that FaLW achieves superior performance. |
| title | FaLW: A Forgetting-aware Loss Reweighting for Long-tailed Unlearning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2601.18650 |