提出结构忠实的删数方法，让模型删数据不丢知识结构。
Stake the Points: Structure-Faithful Instance Unlearning
- 用语义锚点维持删数后知识结构稳定
- 图像分类等任务平均性能提升超19%
- 适合需精准删除数据且保留模型能力的场景
机器删数（MU）旨在缓解预训练模型的隐私风险。核心目标是移除指定数据的影响，同时保留其余知识的可用性。现有方法常忽视保留剩余样本间的语义关系，导致模型出现渐进式结构坍塌，破坏删留平衡。本文提出一种结构忠实的删数框架，引入‘锚点’（stakes）作为语义参考点，以维持知识结构。锚点由语言驱动的属性描述经语义编码器（如CLIP）生成。通过结构感知对齐与正则化机制：前者在删数前后对齐保留知识围绕锚点的组织结构，后者约束关键参数更新。实验表明，在图像分类、检索和人脸识别任务中，性能平均提升32.9%、22.5%和19.3%，有效平衡删留权衡并增强泛化能力。
原文摘要 · Abstract (English)
Machine unlearning (MU) addresses privacy risks in pretrained models. The main goal of MU is to remove the influence of designated data while preserving the utility of retained knowledge. Achieving this goal requires preserving semantic relations among retained instances, which existing studies often overlook. We observe that without such preservation, models suffer from progressive structural collapse, undermining both the deletion-retention balance. In this work, we propose a novel structure-faithful framework that introduces stakes, i.e., semantic anchors that serve as reference points to maintain the knowledge structure. By leveraging these anchors, our framework captures and stabilizes the semantic organization of knowledge. Specifically, we instantiate the anchors from language-driven attribute descriptions encoded by a semantic encoder (e.g., CLIP). We enforce preservation of the knowledge structure via structure-aware alignment and regularization: the former aligns the organization of retained knowledge before and after unlearning around anchors, while the latter regulates updates to structure-critical parameters. Results from image classification, retrieval, and face recognition show average gains of 32.9%, 22.5%, and 19.3% in performance, balancing the deletion-retention trade-off and enhancing generalization.
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。