Domain generalization for zero-calibration brain–computer interfaces with knowledge distillation-based phase invariant feature extraction

The distribution shift of electroencephalography (EEG) data causes poor generalization of brain–computer interfaces (BCIs) in unseen domains. Some methods try to tackle this challenge by collecting a portion of user data for calibration. However, it is time-consuming, mentally fatiguing, and user-unfriendly. To achieve zero-calibration BCIs, most studies employ domain generalization techniques to learn invariant features across different domains in the training set. However, they fail to fully explore invariant features within the same domain, leading to limited performance. In this paper, we present an novel method to learn domain-invariant features from both inter-domain and intra-domain perspectives. For intra-domain invariant features, we propose a knowledge distillation framework to extract EEG phase-invariant features within one domain. As for inter-domain invariant features, correlation alignment is used to bridge distribution gaps across multiple domains. Experimental results on three public datasets validate the effectiveness of our method, showcasing state-of-the-art performance. To the best of our knowledge, this is the first domain generalization study that exploit Fourier phase information as an intra-domain invariant feature to facilitate EEG generalization. More importantly, the zero-calibration BCI based on inter- and intra-domain invariant features has significant potential to advance the practical applications of BCIs in real world. (The code is available on https://github.com/ZilinL/KnIFE).