vertical federated learning (VFL) is a federated learning setting where
multiple parties with different features about the same set of users jointly
train machine learning models without exposing their raw data or model
parameters. Motivated by the rapid growth in VFL research and real
垂直联邦学习是一种联邦学习的类别,在这种类别中,每个客户端共享相同的样本空间,但仅持有特征的子集。本文提出了 Internet Learning(IL),包括其数据分割和网络环境,将性能表现优化为处理客户端的极端动态条件的主要目标。在模拟传感器网络的基础上,通过实现新方法,提出指标并广泛分析结果,证明所开发的方法对网络变化的鲁棒性更优于 VFL 基线。