HHHFL: Hierarchical Heterogeneous Horizontal Federated Learning for Electroencephalography

TL;DR

This paper introduces HHHFL, a hierarchical heterogeneous federated learning method designed for EEG data, addressing data heterogeneity and privacy concerns, and demonstrating improved performance on real-world datasets.

Contribution

The paper proposes a novel hierarchical heterogeneous federated learning framework specifically for EEG data, tackling data heterogeneity and privacy preservation simultaneously.

Findings

Achieves consistent performance improvements across tasks

Effectively handles heterogeneous EEG data from diverse devices

Preserves data privacy during model training

Abstract

Electroencephalography (EEG) classification techniques have been widely studied for human behavior and emotion recognition tasks. But it is still a challenging issue since the data may vary from subject to subject, may change over time for the same subject, and maybe heterogeneous. Recent years, increasing privacy-preserving demands poses new challenges to this task. The data heterogeneity, as well as the privacy constraint of the EEG data, is not concerned in previous studies. To fill this gap, in this paper, we propose a heterogeneous federated learning approach to train machine learning models over heterogeneous EEG data, while preserving the data privacy of each party. To verify the effectiveness of our approach, we conduct experiments on a real-world EEG dataset, consisting of heterogeneous data collected from diverse devices. Our approach achieves consistent performance improvement on every task.