提出可高效删数据的半参数模型，删样本不改参数，速度超现有方法10倍。
Designing to Forget: Deep Semi-parametric Models for Unlearning
- 设计半参数模型，用融合模块存每条数据信息，删数据时无需重训练
- 在ImageNet上删样本后预测误差比重训基线低11%，速度提升超10倍
- 适合需要快速删除敏感数据的场景，如隐私保护或合规需求
近期机器学习中的模型遗忘研究主要聚焦于如何从训练好的模型中移除特定训练样本。然而我们发现，并非所有模型都具有同等的可遗忘性。为此，我们提出一类深度半参数模型（SPMs），其在遗忘阶段表现出非参数特性。SPMs通过融合模块聚合每个训练样本的信息，实现测试时无需修改模型参数即可显式删除指定样本。实验证明，SPMs在图像分类与生成任务中表现与参数模型相当，但在遗忘效率上显著更优。尤其在ImageNet分类任务中，其预测偏差相比重训基线（oracle）降低11%，且遗忘速度比现有参数模型方法快超过10倍。代码已开源：https://github.com/amberyzheng/spm_unlearning。
原文摘要 · Abstract (English)
Recent advances in machine unlearning have focused on developing algorithms to remove specific training samples from a trained model. In contrast, we observe that not all models are equally easy to unlearn. Hence, we introduce a family of deep semi-parametric models (SPMs) that exhibit non-parametric behavior during unlearning. SPMs use a fusion module that aggregates information from each training sample, enabling explicit test-time deletion of selected samples without altering model parameters. Empirically, we demonstrate that SPMs achieve competitive task performance to parametric models in image classification and generation, while being significantly more efficient for unlearning. Notably, on ImageNet classification, SPMs reduce the prediction gap relative to a retrained (oracle) baseline by $11\%$ and achieve over $10\times$ faster unlearning compared to existing approaches on parametric models. The code is available at https://github.com/amberyzheng/spm_unlearning.
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。