通过服务器端梯度冲突缓解与表达实现计算与通信高效的联邦遗忘
Computation and Communication Efficient Federated Unlearning via On-server Gradient Conflict Mitigation and Expression
为视觉模型在联邦场景下提供可撤销数据贡献的机制：通过服务器端梯度冲突缓解与特征编码实现遗忘，视觉研究者可将其用于隐私合规的分布式训练（如医疗影像联邦模型）中移除特定客户端数据的影响。
原文依据 Federated Unlearning (FUL) aims to remove specific participants' data contributions from a trained Federated Learning model
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论联邦遗忘（FUL）旨在从已训练的联邦学习模型中移除特定参与者的数据贡献，从而确保数据隐私并符合监管要求。尽管具有潜力，FUL 的进展受限于若干挑战，包括跨客户端知识不可访问以及高昂的计算与通信成本。为克服这些挑战，我们提出联邦服务器端遗忘（FOUL），一个包含两个关键阶段的新框架。学习以遗忘阶段作为预备学习阶段，在此期间模型识别并编码与遗忘客户端相关的关键特征。该阶段通信高效，并为后续遗忘过程奠定基础。随后，服务器端知识聚合阶段旨在服务器端执行遗忘过程而无需访问客户端数据，从而同时保持效率与隐私。我们为 FUL 引入一种新的数据设置，可对遗忘进行更透明、更严格的评估。为突出我们方法的有效性，我们提出一种名为遗忘时间的新评估指标，用于衡量模型达到最优遗忘性能的速度。在三种数据集上于多种遗忘场景下进行的大量实验表明，FOUL 优于 FUL 中的重训练。此外，FOUL 在显著缩短遗忘时间的同时取得有竞争力或更优的结果，并保持较低的通信与计算成本。
英文原文摘要 1577 字符
Federated Unlearning (FUL) aims to remove specific participants' data contributions from a trained Federated Learning model, thereby ensuring data privacy and compliance with regulatory requirements. Despite its potential, progress in FUL has been limited due to several challenges, including the cross-client knowledge inaccessibility and high computational and communication costs. To overcome these challenges, we propose Federated On-server Unlearning (FOUL), a novel framework that comprises two key stages. The learning-to-unlearn stage serves as a preparatory learning phase, during which the model identifies and encodes the key features associated with the forget clients. This stage is communication-efficient and establishes the basis for the subsequent unlearning process. Subsequently, on-server knowledge aggregation phase aims to perform the unlearning process at the server without requiring access to client data, thereby preserving both efficiency and privacy. We introduce a new data setting for FUL, which enables a more transparent and rigorous evaluation of unlearning. To highlight the effectiveness of our approach, we propose a novel evaluation metric termed time-to-forget, which measures how quickly the model achieves optimal unlearning performance. Extensive experiments conducted on three datasets under various unlearning scenarios demonstrate that FOUL outperforms the Retraining in FUL. Moreover, FOUL achieves competitive or superior results with significantly reduced time-to-forget, while maintaining low communication and computation costs.