Heterogeneous Label Space Transfer Learning for Brain-Computer Interfaces: A Label Alignment Approach

A brain-computer interface (BCI) system usually needs a long calibration session for each new subject/task to adjust its parameters, which impedes its transition from the laboratory to real-world applications. Transfer learning (TL), which leverages labeled data from auxiliary subjects/tasks (source domains), has demonstrated its effectiveness in reducing such calibration effort. Currently, most TL approaches require the source domains to have the same feature space and label space as the target domain, which limits their applications, as the auxiliary data may have different feature spaces and/or different label spaces. This paper considers heterogeneous label spaces transfer learning for BCIs, i.e., the source and target domains have different label spaces. We propose a label alignment (LA) approach to align the source label space to the target label space. It has three desirable properties: 1) LA only needs as few as one labeled sample from each class of the target subject; 2) LA can be used as a preprocessing step before different feature extraction and classification algorithms; and, 3) LA can be integrated with other homogeneous TL approaches to achieve even better performance. Experiments on two motor imagery datasets demonstrated the effectiveness of LA.