Global Adaptive Transformer for Cross-Subject Enhanced EEG Classification

Due to the individual difference, EEG signals from other subjects (source) can hardly be used to decode the mental intentions of the target subject. Although transfer learning methods have shown promising results, they still suffer from poor feature representation or neglect long-range dependencies. In light of these limitations, we propose Global Adaptive Transformer (GAT), an domain adaptation method to utilize source data for cross-subject enhancement. Our method uses parallel convolution to capture temporal and spatial features first. Then, we employ a novel attention-based adaptor that implicitly transfers source features to the target domain, emphasizing the global correlation of EEG features. We also use a discriminator to explicitly drive the reduction of marginal distribution discrepancy by learning against the feature extractor and the adaptor. Besides, an adaptive center loss is designed to align the conditional distribution. With the aligned source and target features, a classifier can be optimized to decode EEG signals. Experiments on two widely used EEG datasets demonstrate that our method outperforms state-of-the-art methods, primarily due to the effectiveness of the adaptor. These results indicate that GAT has good potential to enhance the practicality of BCI.

Automated summary

Due to individual difference, it is difficult to decode the mental intentions of a target subject using EEG signals from other subjects. Existing transfer learning methods have limitations in feature representation and long-range dependencies. To address these limitations, the Global Adaptive Transformer (GAT) is proposed, which utilizes source data for cross-subject enhancement. GAT employs parallel convolution to capture temporal and spatial features, and an attention-based adaptor to transfer source features to the target domain. Experimental results show that GAT outperforms state-of-the-art methods, primarily due to the effectiveness of the adaptor. This indicates that GAT has great potential in enhancing the practicality of BCI.