研究人员开发了一种新颖的“调制学习”技术，能够从每个只有单个数据样本的设备进行协作模型训练。该方法解决了当客户端数据量极少时标准联邦学习的失效问题，而隐私保护噪声进一步加剧了这一问题。该方法通过校准的噪声扰动来转换每个客户端的单个样本，并与中央服务器共享一个后处理表示，以生成与非私有集中式梯度匹配的无偏梯度更新，同时保护数据隐私。 AI
影响 能够从数据量极少的边缘设备进行协作模型训练，增强联邦学习场景中的隐私和效用。
排序理由 该集群包含一篇详细介绍新机器学习技术的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2605.07233v1 Announce Type: cross Abstract: This work focuses on the question of learning from a large number of devices with each device holding only a single sample of data. Several real-world applications exist to this one sample per client setup up including learning fr…
This work focuses on the question of learning from a large number of devices with each device holding only a single sample of data. Several real-world applications exist to this one sample per client setup up including learning from fitness trackers, data/app usage aggregators, b…