Different Set Domain Adaptation for Brain-Computer Interfaces: A Label Alignment Approach

TL;DR

This paper introduces a label alignment method for brain-computer interfaces that enables domain adaptation across different label sets with minimal target data, improving calibration efficiency.

Contribution

A novel label alignment approach for BCI domain adaptation that handles different label spaces with minimal target samples and can be integrated with existing methods.

Findings

Effective in reducing calibration data requirements

Improves performance when adapting across different label sets

Compatible with various feature extraction and classification algorithms

Abstract

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. Domain adaptation, which leverages labeled data from auxiliary subjects/tasks (source domains), has demonstrated its effectiveness in reducing such calibration effort. Currently, most domain adaptation 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 different set domain adaptation for BCIs, i.e., the source and target domains have different label spaces. We introduce a practical setting of different label sets for BCIs, and propose a novel label alignment (LA) approach to align the source label space with 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 domain adaptation approaches to achieve even better performance. Experiments on two motor imagery datasets demonstrated the effectiveness of LA.