A Novel Framework of Horizontal-Vertical Hybrid Federated Learning for EdgeIoT

TL;DR

This paper introduces a hybrid horizontal-vertical federated learning framework for EdgeIoT devices, enabling collaborative model training across devices with different data feature distributions and sample variations, improving federated learning efficiency.

Contribution

The paper proposes a novel HoVeFL framework that combines horizontal and vertical federated learning for EdgeIoT, addressing data heterogeneity and sample non-IID issues.

Findings

HoVeFL achieves lower testing loss with optimized device configurations.

Performance on CIFAR-10 and SVHN datasets demonstrates effectiveness.

The framework effectively handles data feature and sample heterogeneity.

Abstract

This letter puts forth a new hybrid horizontal-vertical federated learning (HoVeFL) for mobile edge computing-enabled Internet of Things (EdgeIoT). In this framework, certain EdgeIoT devices train local models using the same data samples but analyze disparate data features, while the others focus on the same features using non-independent and identically distributed (non-IID) data samples. Thus, even though the data features are consistent, the data samples vary across devices. The proposed HoVeFL formulates the training of local and global models to minimize the global loss function. Performance evaluations on CIFAR-10 and SVHN datasets reveal that the testing loss of HoVeFL with 12 horizontal FL devices and six vertical FL devices is 5.5% and 25.2% higher, respectively, compared to a setup with six horizontal FL devices and 12 vertical FL devices.