让生成模型精准删除特定数据，无需重训练或原始样本。
ContinualFlow: Learning and Unlearning with Neural Flow Matching
- 用能量代理构建重加权损失，软性移除目标数据分布
- 实现与流匹配等效的梯度更新，无需重新训练
- 适用于隐私保护场景，支持可视化验证
我们提出ContinualFlow，一种基于流匹配的生成模型目标化遗忘框架。该方法通过能量基重加权损失，无需从头训练或访问待遗忘样本，即可软性移除数据分布中的特定区域。其核心机制利用能量代理引导遗忘过程，理论上可产生与流匹配等效的梯度，指向一个质量减去的目标分布。我们在二维空间和图像域上进行了实验验证，结合可解释的可视化与定量评估，证明了该框架的有效性。
原文摘要 · Abstract (English)
We introduce ContinualFlow, a principled framework for targeted unlearning in generative models via Flow Matching. Our method leverages an energy-based reweighting loss to softly subtract undesired regions of the data distribution without retraining from scratch or requiring direct access to the samples to be unlearned. Instead, it relies on energy-based proxies to guide the unlearning process. We prove that this induces gradients equivalent to Flow Matching toward a soft mass-subtracted target, and validate the framework through experiments on 2D and image domains, supported by interpretable visualizations and quantitative evaluations.
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。