提出可插拔的遗忘框架ToFU，让联邦学习系统从源头减少数据记忆。
ToFU: Transforming How Federated Learning Systems Forget User Data
- 训练时引入变换操作，降低模型对特定数据的记忆
- 在CIFAR-10/100和MUFAC上显著缩短遗忘时间
- 兼容现有方法，适合注重隐私保护的联邦学习场景
神经网络会无意中记忆训练数据，导致联邦学习（FL）系统存在推理与重建攻击等隐私风险。为缓解此问题并满足隐私法规要求，联邦遗忘（FU）被提出，使参与方能移除其数据对全局模型的影响。然而，现有FU方法多为事后处理，难以高效消除深层记忆。本文主张需从根本上重构系统设计，使其天然支持遗忘。为此，我们提出学习-遗忘协同的Transformed Federated Unlearning（ToFU）框架，在学习过程中引入变换操作以减少对特定样本的记忆。理论分析表明，变换组合可严格约束个体实例信息，从而简化后续遗忘过程。关键的是，ToFU可作为即插即用框架，提升现有FU方法性能。在CIFAR-10、CIFAR-100和MUFAC基准上的实验显示，ToFU优于现有基线，集成后进一步提升性能，并显著降低遗忘时间。
原文摘要 · Abstract (English)
Neural networks unintentionally memorize training data, creating privacy risks in federated learning (FL) systems, such as inference and reconstruction attacks on sensitive data. To mitigate these risks and to comply with privacy regulations, Federated Unlearning (FU) has been introduced to enable participants in FL systems to remove their data's influence from the global model. However, current FU methods primarily act post-hoc, struggling to efficiently erase information deeply memorized by neural networks. We argue that effective unlearning necessitates a paradigm shift: designing FL systems inherently amenable to forgetting. To this end, we propose a learning-to-unlearn Transformation-guided Federated Unlearning (ToFU) framework that incorporates transformations during the learning process to reduce memorization of specific instances. Our theoretical analysis reveals how transformation composition provably bounds instance-specific information, directly simplifying subsequent unlearning. Crucially, ToFU can work as a plug-and-play framework that improves the performance of existing FU methods. Experiments on CIFAR-10, CIFAR-100, and the MUFAC benchmark show that ToFU outperforms existing FU baselines, enhances performance when integrated with current methods, and reduces unlearning time.
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。