Domain-invariant representation learning from EEG with private encoders

David Bethge, Philipp Hallgarten, Tobias Grosse-Puppendahl, Mohamed Kari, Ralf Mikut, Albrecht Schmidt, Ozan Özdenizci

Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in einem KonferenzbandBegutachtung


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.
Titel2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
ISBN (elektronisch)978-1-6654-0540-9
PublikationsstatusVeröffentlicht - 2022
Veranstaltung47th IEEE International Conference on Acoustics, Speech and Signal Processing: ICASSP 2022 - Virtual, Online, Singapur
Dauer: 22 Mai 202227 Mai 2022


Konferenz47th IEEE International Conference on Acoustics, Speech and Signal Processing
KurztitelICASSP 2022
OrtVirtual, Online

ASJC Scopus subject areas

  • Artificial intelligence
  • Signalverarbeitung
  • Biomedizintechnik

Fields of Expertise

  • Human- & Biotechnology
  • Information, Communication & Computing

Dieses zitieren