Signal-Guided Optimization for Machine Unlearning

2026-07-12

AI Summary

Existing machine unlearning methods often suffer from either over-unlearning, which degrades model utility, or under-unlearning, which leaves residual privacy risks, primarily due to the absence of precise guidance signals. To address this, this work proposes the GSUO framework, which introduces, for the first time, a task-aware, fine-grained, and differentiable guidance mechanism that dynamically adjusts unlearning intensity based on the memorization strength of individual samples. GSUO supports diverse unlearning scenarios, including random subsets and class-level removal. Extensive experiments demonstrate that GSUO significantly outperforms 14 baseline methods in terms of unlearning efficacy, model generalization, and computational efficiency, offering a highly effective, reliable, and versatile solution for machine unlearning.

Abstract

Current machine unlearning methods predominantly rely on global, coarse-grained intervention strategies. They lack precise pilot signals to guide the unlearning process and fail to provide differentiable guidance across different unlearning tasks. Due to the varying memorization strengths of samples during original training, such a uniform strategy leads to two problems: some samples are over-unlearned, which harms model utility; while others are under-unlearned, leaving residual information that can be exploited by privacy attacks. In this paper, we propose GSUO, a guidance-signal-aware unlearning optimization framework that designs task-specific fine-grained guidance signals to steer the unlearning process and is applicable to both random-subset and class-wise forgetting tasks. Extensive experiments demonstrate that GSUO outperforms 14 baselines in terms of both unlearning effectiveness and generalization, while achieving high efficiency and significant speedups, validating its effectiveness for reliable machine unlearning.

Problem

• machine unlearning
• guidance signal
• memorization strength
• privacy attack
• unlearning effectiveness

Innovation

• machine unlearning
• guidance signal
• fine-grained optimization
• differentiable unlearning
• memorization-aware