发表机构
Purdue University（普渡大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对机器遗忘问题，受Muon启发提出光谱显著性遗忘（SSU）方法，通过对弱奇异分量设阈值更新，在图像分类器、扩散模型和LLM上验证了其有效性。
AI 中文摘要
机器遗忘（MU）旨在移除特定训练数据的影响，同时保留模型效用。顾名思义，MU可视为学习的逆过程，通过基于梯度的更新抵消先前学习的行为，以减少遗忘集的影响。近期，梯度下降变体Muon被提出，其应用光谱幅度归一化以鼓励探索稀有方向，表现出良好性能。受Muon启发，我们采用光谱视角研究遗忘，提出光谱显著性遗忘（SSU）。SSU对弱奇异分量设置阈值，仅更新有可靠遗忘信号支持的方向，并从遗忘-保留权衡角度为该阈值方法提供理论依据。在图像分类器、扩散模型和大语言模型（LLM）上的实验验证了SSU的有效性。
英文摘要
Machine unlearning (MU) aims to remove the influence of specific training data while preserving model utility. As the name suggests, MU can be viewed as the inverse of learning, using gradient-based updates to reduce the influence of a forget-set by counteracting the previously learned behavior. Recently, Muon, a gradient descent variant, has been introduced. Muon applies spectral magnitude normalization to encourage exploration of rare directions and demonstrates promising performance. Inspired by Muon, we adopt the spectral view for unlearning and propose Spectral Saliency Unlearning (SSU). SSU thresholds weak singular components and updates only those directions supported by a confident unlearning signal. We further provide theoretical justification for this thresholding approach from the perspective of the forgetting-retention trade-off. Experiments across image classifiers, diffusion models, and LLMs demonstrate SSU's effectiveness.
