用特征融合提升联邦学习中删数据时的模型表现，避免误删关键知识。
Image Feature Fusion-based Federated Client Unlearning (FCU)
- 引入线性图像特征融合机制，动态生成混合样本。
- 在医学影像数据集上，遗忘误差接近重训练标准，优于现有方法。
- 适合关注隐私保护与模型泛化平衡的研究者。
主要数据保护法规均提及“被遗忘权”，推动了联邦遗忘（FU）技术的发展。但一个顽固问题依然存在：灾难性遗忘——删除目标知识的同时，也意外丢弃了重要的保留知识，进而损害模型的全局泛化能力。为更好平衡遗忘效果与泛化能力，我们提出基于图像特征融合的联邦客户端遗忘（IFF-FCU）。其核心思想是引入线性图像特征融合机制（Mixup），动态生成混合样本，弥合遗忘分布与保留分布之间的差距。该策略不仅不局限于删除离散数据点，理论上还拓宽并正则化了遗忘边界。我们在医疗影像基准数据集RSNA-ICH和ISIC2018上进行了大量实验，结果表明，该方法实现了较好的遗忘效果。例如，在ICH数据集上，IFF-FCU的遗忘误差接近重训练黄金标准，显著优于现有基线方法。
原文摘要 · Abstract (English)
Major data protection regulations all mention the "right to be forgotten," and that's what pushed federated unlearning (FU) techniques forward. But one stubborn issue remains: catastrophic forgetting--you erase the target knowledge, yet somehow you also end up throwing out essential retained knowledge, which then hurts the model's global generalization. To get a better balance between unlearning effectiveness and generalization ability, we propose something called Image Feature Fusion-based Federated Client Unlearning (IFF-FCU). The idea is to bring in a linear Image Feature Fusion mechanism (Mixup) that dynamically creates mixed samples, bridging the gap between forget-distribution and retain-distribution. What this strategy does isn't just deleting a few discrete data points--it theoretically widens and regularizes the forgetting boundary. We ran extensive experiments on medical imaging benchmarks (RSNA-ICH and ISIC2018), and the results show that our approach achieves reasonably good unlearning. For instance, on the ICH dataset, IFF-FCU achieves a highly competitive Error deviation from the retrained gold standard, demonstrating robust improvements over existing baselines.
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。