FedUP通过轻量滤波器实现秒级联邦遗忘，保留模型性能并可逆恢复知识。
FedUP: One-Shot Federated Unlearning via Centroid-Guided Plug-in Filters
- 用可插拔滤波器作为知识过滤器，仅需一次通信即可完成遗忘。
- 在图像与文本任务中，非目标知识损失降低，遗忘精度优于现有方法。
- 支持知识可逆恢复，适合需合规删除数据的联邦学习场景。
联邦遗忘（FU）对于满足去标识化等法律要求至关重要，但现有方法在非目标知识损失与高请求延迟间存在矛盾。为此，我们提出 FedUP，一种基于轻量级可插拔滤波器的一次性联邦遗忘框架，该滤波器充当“知识漏斗”，筛选出目标数据同时保持原始模型性能。通过冻结原始模型参数，并在服务器端使用差分隐私（DP）保护的类别中心样本训练滤波器，FedUP 避免了多轮客户端-服务器通信和复杂重训练，将遗忘延迟从分钟级降至秒级。此外，其可插拔架构具有内在可逆性，可通过简单移除滤波器无缝恢复被遗忘知识。在多种图像与文本任务上的大量实验表明，FedUP 有效降低非目标知识损失，在不同场景下均实现了更优的遗忘精度与效率。代码已公开：https://github.com/suows/FedUP-code。
原文摘要 · Abstract (English)
Federated unlearning (FU) is critical for complying with legal mandates like the right to be forgotten in decentralized systems, yet current methods face a persistent dilemma between non-target knowledge loss and high request latency. To resolve these issues, we propose FedUP, a one-shot federated unlearning framework utilizing lightweight pluggable filters that act as a "knowledge funnel" to screen out target data while preserving original model performance. By freezing original model parameters and training filters at the server side using differentially private (DP)-protected class centroid samples, FedUP bypasses the need for multi-round client-server communication and complex retraining, reducing unlearning latency from minutes to mere seconds. Additionally, the framework's pluggable architecture ensures inherent reversibility, enabling the seamless restoration of forgotten knowledge by simply removing the filters. Extensive experiments on diverse image and text tasks demonstrate that FedUP effectively reduces non-target knowledge loss and achieves superior unlearning precision and efficiency across various scenarios. Code is available at: https://github.com/suows/FedUP-code.
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。