Lethe:Adapter-Augmented Dual-Stream Update for Persistent Knowledge Erasure in Federated 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_ | 1866911409124671488 |
|---|---|
| author | Tan, Hanwei Hu, Wentai He, Ligang Quan, Yijun |
| author_facet | Tan, Hanwei Hu, Wentai He, Ligang Quan, Yijun |
| contents | Federated unlearning (FU) aims to erase designated client-level, class-level, or sample-level knowledge from a global model. Existing studies commonly assume that the collaboration ends up with the unlearning operation, overlooking the follow-up situation where the federated training continues over the remaining data.We identify a critical failure mode, termed Knowledge resurfacing, by revealing that continued training can re-activate unlearned knowledge and cause the removed influence to resurface in the global model. To address this, we propose Lethe, a novel federated unlearning method that de-correlates knowledge to be unlearned from knowledge to be retained, ensuring persistent erasure during continued training.Lethe follows a Reshape--Rectify--Restore pipeline: a temporary adapter is first trained with gradient ascent on the unlearning data to obtain magnified updates, which is then used as corrective signals to diverge layer-wise rectification on the remaining updates in two streams. Finally, the adapter is removed and a short recovery stage is performed on the retained data. Our experiments show that Lethe supports unlearning in the federated system at all levels in a unified manner and maintains superior persistence (Resurfacing Rate <1% in most cases) even after numerous rounds of follow-up training. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_22601 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Lethe:Adapter-Augmented Dual-Stream Update for Persistent Knowledge Erasure in Federated Unlearning Tan, Hanwei Hu, Wentai He, Ligang Quan, Yijun Machine Learning Federated unlearning (FU) aims to erase designated client-level, class-level, or sample-level knowledge from a global model. Existing studies commonly assume that the collaboration ends up with the unlearning operation, overlooking the follow-up situation where the federated training continues over the remaining data.We identify a critical failure mode, termed Knowledge resurfacing, by revealing that continued training can re-activate unlearned knowledge and cause the removed influence to resurface in the global model. To address this, we propose Lethe, a novel federated unlearning method that de-correlates knowledge to be unlearned from knowledge to be retained, ensuring persistent erasure during continued training.Lethe follows a Reshape--Rectify--Restore pipeline: a temporary adapter is first trained with gradient ascent on the unlearning data to obtain magnified updates, which is then used as corrective signals to diverge layer-wise rectification on the remaining updates in two streams. Finally, the adapter is removed and a short recovery stage is performed on the retained data. Our experiments show that Lethe supports unlearning in the federated system at all levels in a unified manner and maintains superior persistence (Resurfacing Rate <1% in most cases) even after numerous rounds of follow-up training. |
| title | Lethe:Adapter-Augmented Dual-Stream Update for Persistent Knowledge Erasure in Federated Unlearning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2601.22601 |