类别级联邦遗忘：利用师生记忆生成实现主动遗忘
Class-wise Federated Unlearning: Harnessing Active Forgetting with Teacher-Student Memory Generation
AI总结：
针对联邦学习中细粒度数据删除需求，本文提出基于主动遗忘的框架，通过师生学习生成新记忆覆盖目标记忆，并用改进EWC保护非目标知识。
摘要：
与机器学习模型相关的隐私担忧推动了机器遗忘研究，其目标是从已训练模型中擦除特定目标训练数据的记忆。该问题同样出现在联邦学习中，因此需要解决联邦遗忘问题。然而，联邦遗忘仍是一项具有挑战性的任务。一方面，当前研究主要关注遗忘某个客户端的全部数据，忽视了更细粒度的遗忘目标，例如类别级和样本级删除。另一方面，现有方法在数据影响估计方面不够精确，并带来显著的计算或存储负担。为解决这些问题，我们提出一种基于主动遗忘、受神经机制启发的联邦遗忘框架，该框架独立于模型架构，并适用于细粒度遗忘目标。我们的框架与现有方法的区别在于利用新记忆覆盖旧记忆。这些新记忆通过师生学习生成。我们进一步利用改进的弹性权重巩固来缓解非目标数据的灾难性遗忘。在基准数据集上的大量实验证明了本方法的效率和有效性，并在抵御后门攻击方面取得了令人满意的遗忘完整性。
英文摘要：
Privacy concerns associated with machine learning models have driven research into machine unlearning, which aims to erase the memory of specific target training data from already trained models. This issue also arises in federated learning, creating the need to address the federated unlearning problem. However, federated unlearning remains a challenging task. On the one hand, current research primarily focuses on unlearning all data from a client, overlooking more fine-grained unlearning targets, e.g., class-wise and sample-wise removal. On the other hand, existing methods suffer from imprecise estimation of data influence and impose significant computational or storage burden. To address these issues, we propose a neuro-inspired federated unlearning framework based on active forgetting, which is independent of model architectures and suitable for fine-grained unlearning targets. Our framework distinguishes itself from existing methods by utilizing new memories to overwrite old ones. These new memories are generated through teacher-student learning. We further utilize refined elastic weight consolidation to mitigate catastrophic forgetting of non-target data. Extensive experiments on benchmark datasets demonstrate the efficiency and effectiveness of our method, achieving satisfactory unlearning completeness against backdoor attacks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
