New framework enables asynchronous federated unlearning for medical imaging models

作者 PulseAugur 编辑部 · [3 个来源] · 2026-04-29 15:41

Researchers have introduced Asynchronous Federated Unlearning with Invariance Calibration (AFU-IC), a new framework designed for medical imaging applications. This method addresses limitations in existing Federated Unlearning techniques, which often suffer from synchronous coordination delays and temporary erasure of data influence. AFU-IC allows clients to unlearn data asynchronously without halting global training, while a server-side calibration mechanism prevents relearning. Experiments show AFU-IC achieves comparable unlearning efficacy and model fidelity to retraining, with significantly reduced latency. AI

影响 Improves efficiency and compliance for federated learning in sensitive data environments like medical imaging.

排序理由 Academic paper introducing a novel framework for federated unlearning.

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 3 个来源。我们如何撰写摘要 →

报道来源 [3]

arXiv cs.LG TIER_1 English(EN) · Zhaoyuan Cai, Xinglin Zhang · 2026-04-30 04:00

Asynchronous Federated Unlearning with Invariance Calibration for Medical Imaging

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 …
arXiv cs.LG TIER_1 English(EN) · Xinglin Zhang · 2026-04-29 15:41

Asynchronous Federated Unlearning with Invariance Calibration for Medical Imaging

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…
Hugging Face Daily Papers TIER_1 English(EN) · 2026-04-29 15:41

Asynchronous Federated Unlearning with Invariance Calibration for Medical Imaging

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…

报道来源 [3]

Asynchronous Federated Unlearning with Invariance Calibration for Medical Imaging

Asynchronous Federated Unlearning with Invariance Calibration for Medical Imaging

Asynchronous Federated Unlearning with Invariance Calibration for Medical Imaging

相关实体

相关话题