Interference-Aware Multi-Task Unlearning
Quick Take
This paper presents an interference-aware framework for multi-task unlearning in machine learning models.
Key Points
- Introduces full-task and partial-task unlearning.
- Addresses task-level and instance-level interference.
- Achieves up to 52.9% reduction in unlearning interference.
📖 Reader Mode
~2 min readAbstract:Machine unlearning aims to remove the contribution of designated training data from a trained model while preserving performance on the remaining data. Existing work mainly focuses on single-task settings, whereas modern models often operate in multi-task setups with shared backbones, where removing supervision for one task or instance can unintentionally affect others. We introduce multi-task unlearning with two settings: full-task unlearning, which removes a target instance from all tasks, and partial-task unlearning, which removes supervision only from selected tasks. We show that shared parameters couple the forget and retain sets, causing task-level interference on non-target tasks and instance-level interference on other instances. To address this issue, we propose an interference-aware framework that combines task-aware gradient projection, which constrains updates within task-specific subspaces, with instance-level gradient orthogonalization, which reduces conflicts between forget and retain signals. Experiments on two multi-task computer vision benchmarks across five tasks show that our method achieves effective unlearning while maintaining strong generalization, reducing UIS compared with the strongest baseline by 30.3% in full-task unlearning and 52.9% in partial-task unlearning.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2605.19042 [cs.AI] |
| (or arXiv:2605.19042v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2605.19042 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Rui Fang [view email]
[v1]
Mon, 18 May 2026 19:05:40 UTC (864 KB)
— Originally published at arxiv.org
More from arXiv cs.AI
See more →From Prompts to Protocols: An AI Agent for Laboratory Automation
An AI agent integrates large language models for automating laboratory protocols, enhancing efficiency and accuracy.