解耦稀疏表示用于概念分离的扩散撤销
Disentangled Sparse Representations for Concept-Separated Diffusion Unlearning
AI总结：
本文提出SAEParate，通过概念感知对比目标解耦潜在表示，提升扩散模型中特定概念撤销的精度与效果，实验显示在联合风格-物体撤销任务中表现优异。
摘要：
在文本到图像扩散模型中撤销特定概念以防止生成不良内容变得越来越重要。尽管基于稀疏自编码器（SAE）的方法因其通过轻量级操纵潜在特征来抑制目标概念而受到关注，但训练时的稀疏重构目标并未显式强制概念分离，导致概念间共享潜在特征。为此，我们提出SAEParate，通过概念感知对比目标将潜在表示组织成概念特定的簇，从而在减少撤销过程中意外干扰的同时实现更精确的概念抑制。此外，我们通过GeLU为基础的非线性转换增强编码器，提升其在该分离目标下的表达能力，从而获得更具判别性和解耦的潜在空间。在UnlearnCanvas上的实验显示，该方法在联合风格-物体撤销任务中表现尤为突出，这一任务是现有方法在目标与非目标概念之间存在严重干扰的挑战性场景。
英文摘要：
Unlearning specific concepts in text-to-image diffusion models has become increasingly important for preventing undesirable content generation. Among prior approaches, sparse autoencoder (SAE)-based methods have attracted attention due to their ability to suppress target concepts through lightweight manipulation of latent features, without modifying model parameters. However, SAEs trained with sparse reconstruction objectives do not explicitly enforce concept-wise separation, resulting in shared latent features across concepts. To address this, we propose SAEParate, which organizes latent representations into concept-specific clusters via a concept-aware contrastive objective, enabling more precise concept suppression while reducing unintended interference during unlearning. In addition, we enhance the encoder with a GeLU-based nonlinear transformation to increase its expressive capacity under this separation objective, enabling a more discriminative and disentangled latent space. Experiments on UnlearnCanvas demonstrate state-of-the-art performance, with particularly strong gains in joint style-object unlearning, a challenging setting where existing methods suffer from severe interference between target and non-target 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。
