提出可调控的梯度翻转方法，实现对模型遗忘过程的精准控制。
Controllable Machine Unlearning via Gradient Pivoting
- 将遗忘问题重构为多目标优化，通过梯度翻转机制导航帕累托前沿。
- 仅用一个超参数控制遗忘强度，可生成更优且多样化的遗忘结果。
- 适用于需要精细调节数据影响的场景，如隐私保护与模型合规性。
机器遗忘（MU）旨在消除特定数据对训练模型的影响。然而，现有近似遗忘方法通常被建模为单目标优化（SOO），面临遗忘效果与模型保真度之间的显著权衡，导致三大挑战：过度遗忘风险、遗忘过程缺乏细粒度控制，以及缺乏全面评估该权衡的指标。为此，我们重新将MU建模为多目标优化（MOO）问题，并提出一种新算法——基于梯度翻转的可控遗忘（CUP）。其独特的翻转机制不收敛于单一解，而是可调控地遍历整个帕累托前沿。该过程由一个直观的超参数‘遗忘强度’控制，实现对遗忘-保真度权衡的精确选择。为评估能力，我们采用超体积指标（hypervolume indicator），衡量算法生成解集的质量与多样性。实验表明，CUP在多种视觉任务中持续优于现有方法，生成更优的帕累托最优解集。
原文摘要 · Abstract (English)
Machine unlearning (MU) aims to remove the influence of specific data from a trained model. However, approximate unlearning methods, often formulated as a single-objective optimization (SOO) problem, face a critical trade-off between unlearning efficacy and model fidelity. This leads to three primary challenges: the risk of over-forgetting, a lack of fine-grained control over the unlearning process, and the absence of metrics to holistically evaluate the trade-off. To address these issues, we reframe MU as a multi-objective optimization (MOO) problem. We then introduce a novel algorithm, Controllable Unlearning by Pivoting Gradient (CUP), which features a unique pivoting mechanism. Unlike traditional MOO methods that converge to a single solution, CUP's mechanism is designed to controllably navigate the entire Pareto frontier. This navigation is governed by a single intuitive hyperparameter, the `unlearning intensity', which allows for precise selection of a desired trade-off. To evaluate this capability, we adopt the hypervolume indicator, a metric that captures both the quality and diversity of the entire set of solutions an algorithm can generate. Our experimental results demonstrate that CUP produces a superior set of Pareto-optimal solutions, consistently outperforming existing methods across various vision tasks.
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。