从扩散模型中实现可分离的多概念擦除
Separable Multi-Concept Erasure from Diffusion Models
AI总结：
提出SepME方法，通过生成概念无关表示和权重解耦，实现扩散模型中多概念的可分离擦除与恢复，保持生成性能。
摘要：
大规模扩散模型以其令人印象深刻的图像生成能力而闻名，但也引发了研究人员对其社会影响的担忧，例如模仿受版权保护的艺术风格。为此，现有方法转向机器遗忘技术，以从预训练模型中消除不安全的概念。然而，这些方法损害了生成性能，忽视了多概念擦除之间的耦合，以及概念恢复问题。为解决这些问题，我们提出了一种可分离的多概念擦除器（SepME），主要包括两部分：生成与概念无关的表示和权重解耦。前者旨在避免遗忘与遗忘概念无关的大量信息。后者分离可优化的模型权重，使每个权重增量对应于特定概念的擦除，而不影响其他概念的生成性能。具体而言，用于擦除指定概念的权重增量被表述为基于其他已知不良概念计算出的解的线性组合。大量实验表明，我们的方法在消除概念、保持模型性能以及提供各种概念擦除或恢复的灵活性方面是有效的。
英文摘要：
Large-scale diffusion models, known for their impressive image generation capabilities, have raised concerns among researchers regarding social impacts, such as the imitation of copyrighted artistic styles. In response, existing approaches turn to machine unlearning techniques to eliminate unsafe concepts from pre-trained models. However, these methods compromise the generative performance and neglect the coupling among multi-concept erasures, as well as the concept restoration problem. To address these issues, we propose a Separable Multi-concept Eraser (SepME), which mainly includes two parts: the generation of concept-irrelevant representations and the weight decoupling. The former aims to avoid unlearning substantial information that is irrelevant to forgotten concepts. The latter separates optimizable model weights, making each weight increment correspond to a specific concept erasure without affecting generative performance on other concepts. Specifically, the weight increment for erasing a specified concept is formulated as a linear combination of solutions calculated based on other known undesirable concepts. Extensive experiments indicate the efficacy of our approach in eliminating concepts, preserving model performance, and offering flexibility in the erasure or recovery of various concepts.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
