提出首个垂直联邦学习标签遗忘方法，实现隐私保护下的高效数据擦除。
Towards Privacy-Guaranteed Label Unlearning in Vertical Federated Learning: Few-Shot Forgetting without Disclosure
- 用表示层混合生成合成嵌入，避免直接暴露标签信息。
- 梯度遗忘使模型彻底移除特定标签痕迹，保留其他数据性能。
- 适合需合规删除用户标签的医疗、金融等高隐私场景使用。
本文针对垂直联邦学习（VFL）中长期被忽视的标签遗忘问题，提出首个专为标签遗忘设计的方法。在VFL中，标签既是关键输入又是敏感信息。为此，我们采用表示层面的流形混合机制，为待遗忘和保留样本生成合成嵌入，增强后续梯度遗忘与恢复步骤的信号。通过梯度级标签遗忘，有效从模型中移除关联标签信息；为恢复保留数据性能，引入优化阶段以精炼剩余嵌入。在MNIST、CIFAR-10、CIFAR-100、ModelNet、Brain Tumor MRI、COVID-19 Radiography和Yahoo Answers等多个数据集上验证，方法具备强效性与可扩展性。本工作为VFL中的遗忘学习开辟新方向，证明将mixup重用于高效、保用的遗忘机制具有可行性。代码已开源。
原文摘要 · Abstract (English)
This paper addresses the critical challenge of unlearning in Vertical Federated Learning (VFL), a setting that has received far less attention than its horizontal counterpart. Specifically, we propose the first method tailored to \textit{label unlearning} in VFL, where labels play a dual role as both essential inputs and sensitive information. To this end, we employ a representation-level manifold mixup mechanism to generate synthetic embeddings for both unlearned and retained samples. This is to provide richer signals for the subsequent gradient-based label forgetting and recovery steps. These augmented embeddings are then subjected to gradient-based label forgetting, effectively removing the associated label information from the model. To recover performance on the retained data, we introduce a recovery-phase optimization step that refines the remaining embeddings. This design achieves effective label unlearning while maintaining computational efficiency. We validate our method through extensive experiments on diverse datasets, including MNIST, CIFAR-10, CIFAR-100, ModelNet, Brain Tumor MRI, COVID-19 Radiography, and Yahoo Answers demonstrate strong efficacy and scalability. Overall, this work establishes a new direction for unlearning in VFL, showing that re-imagining mixup as an efficient mechanism can unlock practical and utility-preserving unlearning. The code is publicly available at https://github.com/bryanhx/Towards-Privacy-Guaranteed-Label-Unlearning-in-Vertical-Federated-Learning
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。