Inter-subject Deep Transfer Learning for Motor Imagery EEG Decoding
This work addresses a key bottleneck in EEG-based brain-computer interfaces by enabling effective multi-subject training without performance degradation, which is incremental but important for practical applications.
The paper tackled the negative transfer problem in training convolutional neural networks on multiple subjects' EEG data for motor imagery decoding, proposing a multi-branch deep transfer network (SCSN) and an MMD-enhanced version (SCSN-MMD) that achieved performance improvements, with SCSN-MMD reaching 54.8% accuracy compared to a benchmark CNN's 48.8% on an online dataset.
Convolutional neural networks (CNNs) have become a powerful technique to decode EEG and have become the benchmark for motor imagery EEG Brain-Computer-Interface (BCI) decoding. However, it is still challenging to train CNNs on multiple subjects' EEG without decreasing individual performance. This is known as the negative transfer problem, i.e. learning from dissimilar distributions causes CNNs to misrepresent each of them instead of learning a richer representation. As a result, CNNs cannot directly use multiple subjects' EEG to enhance model performance directly. To address this problem, we extend deep transfer learning techniques to the EEG multi-subject training case. We propose a multi-branch deep transfer network, the Separate-Common-Separate Network (SCSN) based on splitting the network's feature extractors for individual subjects. We also explore the possibility of applying Maximum-mean discrepancy (MMD) to the SCSN (SCSN-MMD) to better align distributions of features from individual feature extractors. The proposed network is evaluated on the BCI Competition IV 2a dataset (BCICIV2a dataset) and our online recorded dataset. Results show that the proposed SCSN (81.8%, 53.2%) and SCSN-MMD (81.8%, 54.8%) outperformed the benchmark CNN (73.4%, 48.8%) on both datasets using multiple subjects. Our proposed networks show the potential to utilise larger multi-subject datasets to train an EEG decoder without being influenced by negative transfer.