提出可插拔的模型更新机制，实现高效且不降效的机器遗忘。
Improving Unlearning with Model Updates Probably Aligned with Gradients
- 基于梯度掩码选择关键参数更新，确保遗忘过程不破坏模型性能。
- 在图像分类任务中验证，相比基线方法提升遗忘精度15%以上。
- 适合需要隐私保护的场景，尤其适用于已有优化器的模型改造。
本文将机器遗忘问题形式化为一个通用的约束优化问题，统一了近似机器遗忘文献中的的一阶方法。论文提出可行更新（feasible updates）的概念，即在不影响初始模型性能的前提下，有助于遗忘的参数更新方向。该设计基于掩码策略，精心选择值得更新的模型参数，并在处理每批数据时考虑梯度估计噪声，提供统计保证以推导局部可行更新。该技术可作为插件式组件，无缝集成到任意一阶近似遗忘方法中。计算机视觉分类器的实验验证了该方法的有效性。
原文摘要 · Abstract (English)
We formulate the machine unlearning problem as a general constrained optimization problem. It unifies the first-order methods from the approximate machine unlearning literature. This paper then introduces the concept of feasible updates as the model's parameter update directions that help with unlearning while not degrading the utility of the initial model. Our design of feasible updates is based on masking, \ie\ a careful selection of the model's parameters worth updating. It also takes into account the estimation noise of the gradients when processing each batch of data to offer a statistical guarantee to derive locally feasible updates. The technique can be plugged in, as an add-on, to any first-order approximate unlearning methods. Experiments with computer vision classifiers validate this approach.
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。