提出高效遗忘框架，精准移除模型中特定数据影响而不重训。
Train Once, Forget Precisely: Anchored Optimization for Efficient Post-Hoc Unlearning
- 将遗忘建模为带约束的优化问题，用L2正则锚定参数不变。
- 在CIFAR-10和ImageNet-100上实现高保留性能，计算开销极低。
- 支持类别、概念、风格等多类遗忘，可验证且可扩展。
随着机器学习系统日益依赖受隐私法规约束的数据，从训练好的模型中选择性地消除特定信息变得至关重要。在图像分类任务中，这涉及移除特定训练样本、语义类别或视觉风格的影响，而无需完全重新训练。我们提出 extbf{Forget-Aligned Model Reconstruction (FAMR)}，一个理论基础扎实且计算高效的深度图像分类器后训练遗忘框架。FAMR将遗忘建模为一个约束优化问题：在遗忘集上最小化统一预测损失，同时通过ℓ₂惩罚项将模型参数锚定在原始值附近。理论分析表明，FAMR的解与基于影响函数的重训练近似相关，且给出了参数与输出偏差的界。在CIFAR-10和ImageNet-100上的类别遗忘任务实验显示，FAMR在保持强性能的同时，仅需极小计算开销。该框架可自然推广至概念与风格擦除，为视觉模型提供一种可扩展且可验证的高效后训练遗忘路径。
原文摘要 · Abstract (English)
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.
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。