Advancing Cross-Subject Domain Generalization in Brain-Computer Interfaces With Multiadversarial Strategies

• Published in: IEEE transactions on instrumentation and measurement Vol. 74; pp. 1 - 12
• Main Authors: Liu, Yici, Qin, Lang, Chen, Xin, Le Bouquin Jeannes, Regine, Louis Coatrieux, Jean, Shu, Huazhong
• Format: Journal Article
• Language: English
• Published: New York IEEE 2025; The Institute of Electrical and Electronics Engineers, Inc. (IEEE); Institute of Electrical and Electronics Engineers
• Subjects: Adversarial neural network; Bioengineering; Brain modeling; Costs; Data augmentation; Data mining; Data models; Datasets; domain generalization (DG); electroencephalographic (EEG); Electroencephalography; Fatigue tests; Feature extraction; Human-computer interface; Life Sciences; Manifolds; Space mapping; Training; transfer learning; transfer learning; Costs; Space mapping; domain generalization (DG); Adversarial neural network; Electroencephalography; Data mining; Manifolds; Training; electroencephalographic (EEG); Data augmentation; Feature extraction; Brain modeling; Data models
• ISSN: 0018-9456; 1557-9662; 1557-9662
• DOI: 10.1109/TIM.2025.3566804

A cross-subject domain generalization (DG) approach with multiadversarial strategies (DGMA) is introduced to reduce brain-computer interfaces (BCIs) systems' dependency on high-quality, subject-specific electroencephalographic (EEG) data, making it adaptable to unseen domains. DGMA leverages annotated training data from other subjects and consists of three modules: 1) prefeature extraction (PFE), enhancing EEG signal separability through preprocessing, data augmentation, and tangent space mapping; 2) distribution feature updater (DFU), aligning intersubject feature distributions with marginal maximum mean discrepancy (MMD); and 3) multiadversarial training (MAT), initially using gradient reversal layer (GRL) to amplify domain differences and classification loss, allowing the model to learn diverse domain-specific features before minimizing these differences to balance domain transferability and discriminability. DGMA is capable of better capturing domain-specific features while achieving stronger generalization compared with traditional methods focused solely on minimizing domain differences. Validated on four motor imagery datasets, DGMA achieved state-of-the-art accuracies of 76.1% on BCI Competition IV 2a and 72.4% on the 002-2014 dataset. Additional tests on a private fatigue dataset and the SEED dataset yielded accuracies of 99.5% and 86.6%, respectively. The code can be found at https://github.com/liuyici/DGMA-BCI