Train Once, Forget Precisely: Anchored Optimization for Efficient Post-Hoc Unlearning
This addresses privacy regulation needs in machine learning by enabling efficient post-hoc unlearning for vision models, though it is incremental as it builds on existing unlearning methods.
The paper tackles the problem of selectively removing specific information from trained image classifiers without full retraining, introducing the FAMR framework that achieves strong performance retention with minimal computational overhead on datasets like CIFAR-10 and ImageNet-100.
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.