研究人员推出了一种名为“不变性校准的异步联邦遗忘”（AFU-IC）的新框架，专为医学影像应用设计。该方法解决了现有联邦遗忘技术在同步协调延迟和数据影响临时擦除方面的局限性。AFU-IC 允许客户端异步遗忘数据，而无需中断全局训练，同时服务器端的校准机制可防止重新学习。实验表明，AFU-IC 在遗忘效果和模型保真度方面可与重新训练相媲美，同时显著降低了延迟。 AI
影响 提高了在医学影像等敏感数据环境下的联邦学习效率和合规性。
排序理由 学术论文，介绍了一种新颖的联邦遗忘框架。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2604.26809v1 Announce Type: new Abstract: Federated Unlearning (FU) is an emerging paradigm in Federated Learning (FL) that enables participating clients to fully remove their contributions from a trained global model, driven by data protection regulations that mandate the …
Federated Unlearning (FU) is an emerging paradigm in Federated Learning (FL) that enables participating clients to fully remove their contributions from a trained global model, driven by data protection regulations that mandate the right to be forgotten. However, existing FU meth…
Federated Unlearning (FU) is an emerging paradigm in Federated Learning (FL) that enables participating clients to fully remove their contributions from a trained global model, driven by data protection regulations that mandate the right to be forgotten. However, existing FU meth…