利用数据自身损失值动态重加权，提升模型遗忘效果。
LoReUn: Data Itself Implicitly Provides Cues to Improve Machine Unlearning
- 根据数据损失值自动调整遗忘权重，区分难易程度。
- 在图像分类与生成任务中显著缩小与理想遗忘的差距。
- 适合需精准清除有害内容的文本到图像生成场景。
近期生成模型面临产生有害内容的重大风险，这凸显了机器遗忘（MU）作为消除不良数据影响的关键技术的重要性。然而，现有MU方法通常对所有待遗忘数据赋予相同权重，难以有效遗忘某些更难被遗忘的数据。本文通过实证表明，数据本身的损失值可隐式反映其遗忘难度的差异。基于此洞察，我们提出损失驱动重加权遗忘（LoReUn），一种简单高效的即插即用策略，在遗忘过程中动态调整数据权重，仅带来极小的额外计算开销。该方法在图像分类与生成任务中显著缩小了现有MU方法与理想遗忘之间的差距，有效提升了文本到图像扩散模型防止有害内容生成的能力。
原文摘要 · Abstract (English)
Recent generative models face significant risks of producing harmful content, which has underscored the importance of machine unlearning (MU) as a critical technique for eliminating the influence of undesired data. However, existing MU methods typically assign the same weight to all data to be forgotten, which makes it difficult to effectively forget certain data that is harder to unlearn than others. In this paper, we empirically demonstrate that the loss of data itself can implicitly reflect its varying difficulty. Building on this insight, we introduce Loss-based Reweighting Unlearning (LoReUn), a simple yet effective plug-and-play strategy that dynamically reweights data during the unlearning process with minimal additional computational overhead. Our approach significantly reduces the gap between existing MU methods and exact unlearning in both image classification and generation tasks, effectively enhancing the prevention of harmful content generation in text-to-image diffusion 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。