mixEEG: Enhancing EEG Federated Learning for Cross-subject EEG Classification with Tailored mixup
This work addresses privacy and data scarcity issues in EEG analysis for medical and research applications, though it is incremental as it adapts existing techniques to a new setting.
The paper tackles cross-subject EEG classification by proposing mixEEG, a federated learning framework that uses tailored mixup to share unlabeled averaged data instead of raw data, enhancing model transferability across subjects while preserving privacy, with experiments showing consistent improvements on epilepsy detection and emotion recognition datasets.
The cross-subject electroencephalography (EEG) classification exhibits great challenges due to the diversity of cognitive processes and physiological structures between different subjects. Modern EEG models are based on neural networks, demanding a large amount of data to achieve high performance and generalizability. However, privacy concerns associated with EEG pose significant limitations to data sharing between different hospitals and institutions, resulting in the lack of large dataset for most EEG tasks. Federated learning (FL) enables multiple decentralized clients to collaboratively train a global model without direct communication of raw data, thus preserving privacy. For the first time, we investigate the cross-subject EEG classification in the FL setting. In this paper, we propose a simple yet effective framework termed mixEEG. Specifically, we tailor the vanilla mixup considering the unique properties of the EEG modality. mixEEG shares the unlabeled averaged data of the unseen subject rather than simply sharing raw data under the domain adaptation setting, thus better preserving privacy and offering an averaged label as pseudo-label. Extensive experiments are conducted on an epilepsy detection and an emotion recognition dataset. The experimental result demonstrates that our mixEEG enhances the transferability of global model for cross-subject EEG classification consistently across different datasets and model architectures. Code is published at: https://github.com/XuanhaoLiu/mixEEG.