提出高效精准的扩散模型概念删除方法，支持大规模无损删减。
Forget Many, Forget Right: Scalable and Precise Concept Unlearning in Diffusion Models
- 通过谱迹正则与几何对齐稳定优化过程，避免权重冲突。
- 利用信息解耦器定位目标概念参数，实现精准删除不伤及其他内容。
- 无需额外数据或子模型，可删除最多5倍于基线的概念，适合大规模应用。
文本生成图像的扩散模型虽取得显著进展，但引发版权和滥用担忧，推动机器遗忘研究。然而，将多概念遗忘扩展至大规模场景仍面临三大挑战：(i) 权重更新冲突，导致遗忘失败或生成质量下降；(ii) 机制不精确，造成相似内容的误删；(iii) 依赖额外数据或模块，带来可扩展性瓶颈。为此，我们提出适用于大规模遗忘的统一框架 ScaPre。ScaPre 引入冲突感知的稳定设计，结合谱迹正则化与几何对齐，稳定优化过程，抑制冲突，保持全局结构。同时，信息解耦器识别与概念相关的参数并自适应重设更新，严格限制遗忘仅作用于目标子空间。ScaPre 实现无需辅助数据或子模型的闭式解。在物体、风格及敏感内容上的全面实验表明，该方法能有效移除目标概念且保持生成质量。其在可接受质量范围内遗忘的概念数量是最佳基线的×5倍，实现了大规模遗忘的最先进精度与效率。代码已开源：https://github.com/kaiyuan02415/scapre
原文摘要 · Abstract (English)
Text-to-image diffusion models have achieved remarkable progress, yet their use raises copyright and misuse concerns, prompting research into machine unlearning. However, extending multi-concept unlearning to large-scale scenarios remains difficult due to three challenges: (i) conflicting weight updates that hinder unlearning or degrade generation; (ii) imprecise mechanisms that cause collateral damage to similar content; and (iii) reliance on additional data or modules, creating scalability bottlenecks. To address these, we propose Scalable-Precise Concept Unlearning (ScaPre), a unified framework tailored for large-scale unlearning. ScaPre introduces a conflict-aware stable design, integrating spectral trace regularization and geometry alignment to stabilize optimization, suppress conflicts, and preserve global structure. Furthermore, an Informax Decoupler identifies concept-relevant parameters and adaptively reweights updates, strictly confining unlearning to the target subspace. ScaPre yields an efficient closed-form solution without requiring auxiliary data or sub-models. Comprehensive experiments on objects, styles, and explicit content demonstrate that ScaPre effectively removes target concepts while maintaining generation quality. It forgets up to $\times \mathbf{5}$ more concepts than the best baseline within acceptable quality limits, achieving state-of-the-art precision and efficiency for large-scale unlearning. Code is available at https://github.com/kaiyuan02415/scapre
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。