论文标题
Fedembed：个性化的私人联邦学习
FedEmbed: Personalized Private Federated Learning
论文作者
论文摘要
联合学习可以将机器学习的部署到集中数据收集不切实际的问题。添加差异隐私保证在数据有助于全球模型的同时，保证了隐私的界限。在联合学习中增加个性化会引入新的挑战，因为我们必须考虑单个用户的偏好，在这些用户的偏好中，数据样本可能具有冲突的标签，因为用户的一个子人群可能会积极地查看一个输入，但其他子群体却负面看法相同的输入。我们提出了Fedembed，这是一种新的私人联合学习方法，用于个性化使用（1）类似用户的子选集的全球模型，以及（2）个人嵌入。我们证明，当前的联邦学习方法不足以用矛盾的标签处理数据，并且我们表明，与基线方法相比，Fedembed可以提高45％的改善，以实现个性化的私人联盟学习。
Federated learning enables the deployment of machine learning to problems for which centralized data collection is impractical. Adding differential privacy guarantees bounds on privacy while data are contributed to a global model. Adding personalization to federated learning introduces new challenges as we must account for preferences of individual users, where a data sample could have conflicting labels because one sub-population of users might view an input positively, but other sub-populations view the same input negatively. We present FedEmbed, a new approach to private federated learning for personalizing a global model that uses (1) sub-populations of similar users, and (2) personal embeddings. We demonstrate that current approaches to federated learning are inadequate for handling data with conflicting labels, and we show that FedEmbed achieves up to 45% improvement over baseline approaches to personalized private federated learning.
