提出一种无需修改模型的联邦遗忘新方法，高效移除数据且不影响其他数据性能。
$f$-FUM: Federated Unlearning via min--max and $f$-divergence
- 通过极小-极大优化框架，用f散度衡量数据移除效果
- 比直接重训快得多，对保留数据影响小
- 可插件式接入任意联邦学习系统，适用性广
联邦学习（FL）在保护数据隐私的同时实现分布式协作训练，但随着“被遗忘权”等法律要求及数据投毒攻击风险上升，亟需可解释的数据遗忘机制。与集中式场景不同，联邦学习中难以直接移除特定数据贡献。本文提出一种新型联邦遗忘框架，将其建模为一个极小-极大优化问题：最大化包含所有数据与移除指定数据后模型之间的f散度，同时最小化对保留数据性能的损害。该框架可作为插件嵌入几乎任何联邦学习系统，无需修改模型结构或权重，区别于现有需要服务器模型退化的方案（如 extcite{10269017}）或依赖模型架构调整的方法（如 extcite{khalil2025notfederatedunlearningweight}）。实验表明，该方法在保持模型性能的同时，显著优于朴素重训，在效率上实现大幅加速。
原文摘要 · Abstract (English)
Federated Learning (FL) has emerged as a powerful paradigm for collaborative machine learning across decentralized data sources, preserving privacy by keeping data local. However, increasing legal and ethical demands, such as the "right to be forgotten", and the need to mitigate data poisoning attacks have underscored the urgent necessity for principled data unlearning in FL. Unlike centralized settings, the distributed nature of FL complicates the removal of individual data contributions. In this paper, we propose a novel federated unlearning framework formulated as a min-max optimization problem, where the objective is to maximize an $f$-divergence between the model trained with all data and the model retrained without specific data points, while minimizing the degradation on retained data. Our framework could act like a plugin and be added to almost any federated setup, unlike SOTA methods like (\cite{10269017} which requires model degradation in server, or \cite{khalil2025notfederatedunlearningweight} which requires to involve model architecture and model weights). This formulation allows for efficient approximation of data removal effects in a federated setting. We provide empirical evaluations to show that our method achieves significant speedups over naive retraining, with minimal impact on utility.
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。