Domain-Invariant Representation Learning from EEG with Private Encoders
This addresses privacy-preserving representation learning for EEG data in clinical settings, offering an incremental improvement over existing methods.
The paper tackles poor generalization in EEG signal processing due to distribution shifts by proposing a multi-source learning architecture with private encoders for domain-invariant representations, achieving state-of-the-art performance in EEG-based emotion classification.
Deep learning based electroencephalography (EEG) signal processing methods are known to suffer from poor test-time generalization due to the changes in data distribution. This becomes a more challenging problem when privacy-preserving representation learning is of interest such as in clinical settings. To that end, we propose a multi-source learning architecture where we extract domain-invariant representations from dataset-specific private encoders. Our model utilizes a maximum-mean-discrepancy (MMD) based domain alignment approach to impose domain-invariance for encoded representations, which outperforms state-of-the-art approaches in EEG-based emotion classification. Furthermore, representations learned in our pipeline preserve domain privacy as dataset-specific private encoding alleviates the need for conventional, centralized EEG-based deep neural network training approaches with shared parameters.