提出双优化器机制，让机器遗忘更稳定高效。
DualOptim: Enhancing Efficacy and Stability in Machine Unlearning with Dual Optimizers
- 用自适应学习率和解耦动量因子提升遗忘稳定性。
- 在图像分类、生成和大模型任务中显著提升遗忘效果。
- 适合需要可靠遗忘能力的AI系统部署场景。
现有机器遗忘方法对超参数敏感，需精细调参，限制了实际应用。本文首次实证表明，主流遗忘方法在不同场景下存在不稳定性与性能不佳问题。为此，我们提出双优化器（DualOptim），引入自适应学习率和解耦动量因子。实证与理论分析均证明，DualOptim可有效提升遗忘的稳定性与效率。大量实验显示，其在图像分类、图像生成及大语言模型等多样任务中均显著增强遗忘性能，是一种通用性强的遗忘增强方案。
原文摘要 · Abstract (English)
Existing machine unlearning (MU) approaches exhibit significant sensitivity to hyperparameters, requiring meticulous tuning that limits practical deployment. In this work, we first empirically demonstrate the instability and suboptimal performance of existing popular MU methods when deployed in different scenarios. To address this issue, we propose Dual Optimizer (DualOptim), which incorporates adaptive learning rate and decoupled momentum factors. Empirical and theoretical evidence demonstrates that DualOptim contributes to effective and stable unlearning. Through extensive experiments, we show that DualOptim can significantly boost MU efficacy and stability across diverse tasks, including image classification, image generation, and large language models, making it a versatile approach to empower existing MU algorithms.
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。