解决多任务模型中删除数据时干扰其他任务的问题。
Interference-Aware Multi-Task Unlearning
- 区分全任务与部分任务删改，用梯度投影和正交化减少干扰。
- 在五个视觉任务上实验，全任务删改误删率降30.3%，部分任务降52.9%。
- 适合需精准删除数据且维护多任务性能的部署场景。
机器遗忘旨在移除指定训练数据对已训练模型的影响，同时保持剩余数据的性能。现有工作主要集中在单任务设置，而现代模型常采用共享主干的多任务架构，删除某一任务或实例的监督信号可能无意中影响其他任务。本文提出多任务遗忘的两种设定：全任务遗忘（从所有任务中移除目标实例）与部分任务遗忘（仅从选定任务中移除监督）。我们发现共享参数会耦合遗忘集与保留集，导致任务级干扰（非目标任务受影响）和实例级干扰（其他实例受影响）。为此，提出一种干扰感知框架，结合任务级梯度投影（限制更新在任务特定子空间内）与实例级梯度正交化（降低遗忘与保留信号间的冲突）。在两个多任务计算机视觉基准上跨五项任务的实验表明，该方法实现了有效遗忘并维持强泛化能力，在全任务遗忘中相比最强基线降低30.3%的误删率（UIS），部分任务遗忘中降低52.9%。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。