AI 中文总结
针对扩散模型顺序删除请求导致遗忘失效的问题，提出基于已完成删除转移方向正则化的持续遗忘框架，通过单侧惩罚和固定容量转移库，在少量记忆下平衡删除持久性与生成效用。
AI 中文摘要
扩散模型中的数据遗忘旨在移除特定训练样本的影响，同时不抑制它们所代表的更广泛概念。然而，当删除请求按顺序到达时，针对新请求的更新可能会降低生成效用，并削弱先前删除的效果。我们提出了一种持续数据遗忘框架，该框架利用已完成的删除转移作为方向性参考，以正则化未来的更新。对于每个请求，我们记录在遗忘前后，去噪器在相同固定噪声输入上的响应变化。我们不是匹配完整的删除后响应，而是应用一种单侧惩罚，该惩罚阻止相对于删除后参考沿记录方向的反转，同时不惩罚正交的响应变化以及超出这些参考的进展。为了使存储与请求数量无关，我们维护一个固定容量的代表性转移记录库。记录的选择基于其记录方向上进展对参数更新的局部敏感性，使得即使其惩罚不活跃，这些记录也能被保留。实证评估表明，随着请求的累积，所提出的框架在删除持久性和生成效用之间取得了比现有遗忘基线更好的平衡，且仅使用少量转移记忆。
英文摘要
Data unlearning in diffusion models aims to remove the influence of specific training examples without suppressing the broader concepts they represent. However, when deletion requests arrive sequentially, updates for new requests can degrade generative utility and undermine earlier deletions. We propose a continual data unlearning framework that uses completed deletion transitions as directional references to regularize future updates. For each request, we record changes in denoiser responses on the same fixed noisy inputs before and after unlearning. Rather than matching full post-deletion responses, we apply a one-sided penalty that discourages reversal along the recorded directions relative to the post-deletion references, while leaving orthogonal response changes and progress beyond these references unpenalized. To keep storage independent of the number of requests, we maintain a fixed-capacity bank of representative transition records. Records are selected based on the local sensitivity of progress along their recorded directions to parameter updates, allowing them to be retained even when their penalties are inactive. Empirical evaluations show that the proposed framework achieves a better balance between deletion persistence and generative utility than existing unlearning baselines as requests accumulate, using only a small transition memory.
CommentsPreprint
