一次训练，精准遗忘：用于高效事后遗忘的锚定优化
Train Once, Forget Precisely: Anchored Optimization for Efficient Post-Hoc Unlearning
AI总结：
针对深度图像分类器的事后遗忘问题，提出FAMR框架，通过锚定优化的约束方法在遗忘集上最小化预测损失，在保证模型性能的同时实现高效且可扩展的样本、概念及风格遗忘。
摘要：
随着机器学习系统愈发依赖受隐私法规约束的数据，从已训练模型中选择性遗忘特定信息已变得至关重要。在图像分类领域，这意味着无需完整重新训练，就能消除特定训练样本、语义类别或视觉风格的影响。我们提出了**遗忘对齐模型重构（FAMR）**，这是一个具备理论支撑且计算高效的深度图像分类器事后遗忘框架。FAMR将遗忘问题建模为带约束的优化任务：在遗忘集上最小化均匀预测损失，同时通过$\ell_2$惩罚项将模型参数锚定至原始值。理论分析将FAMR的解与基于影响函数的重训练近似方法关联起来，并给出了参数偏差和输出偏差的界。在CIFAR-10和ImageNet-100数据集上开展的类别遗忘实验结果表明，FAMR效果显著，既能保持良好的模型性能，又只需极低的计算开销。该框架可自然推广至概念擦除和风格擦除场景，为视觉模型的高效事后遗忘提供了一条可扩展且可验证的实现路径。
英文摘要：
As machine learning systems increasingly rely on data subject to privacy regulation, selectively unlearning specific information from trained models has become essential. In image classification, this involves removing the influence of particular training samples, semantic classes, or visual styles without full retraining. We introduce \textbf{Forget-Aligned Model Reconstruction (FAMR)}, a theoretically grounded and computationally efficient framework for post-hoc unlearning in deep image classifiers. FAMR frames forgetting as a constrained optimization problem that minimizes a uniform-prediction loss on the forget set while anchoring model parameters to their original values via an $\ell_2$ penalty. A theoretical analysis links FAMR's solution to influence-function-based retraining approximations, with bounds on parameter and output deviation. Empirical results on class forgetting tasks using CIFAR-10 and ImageNet-100 demonstrate FAMR's effectiveness, with strong performance retention and minimal computational overhead. The framework generalizes naturally to concept and style erasure, offering a scalable and certifiable route to efficient post-hoc forgetting in vision models.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
