Domain-Invariant Representation Learning from EEG with Private Encoders

Bethge, David; Hallgarten, Philipp; Grosse-Puppendahl, Tobias; Kari, Mohamed; Mikut, Ralf; Schmidt, Albrecht und Özdenizci, Ozan (2022): Domain-Invariant Representation Learning from EEG with Private Encoders. ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Singapore, Singapore, 23-27 May 2022. In: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), S. 1236-1240

Abstract

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.

• Dokumententyp: Konferenzbeitrag (Paper)
• Fakultät: Mathematik, Informatik und Statistik > Informatik
• Themengebiete: 000 Informatik, Informationswissenschaft, allgemeine Werke > 004 Informatik
• Sprache: Englisch