Revisiting Euclidean Alignment for Transfer Learning in EEG-Based Brain-Computer Interfaces

TL;DR

This paper revisits Euclidean alignment (EA), a transfer learning technique for EEG-based BCIs, clarifying its methodology, exploring its applications, and suggesting future research directions to improve cross-subject EEG decoding.

Contribution

It provides a comprehensive review of EA, explaining its correct usage, applications, extensions, and potential new research avenues in EEG transfer learning.

Findings

EA effectively reduces data distribution discrepancies across subjects.

Numerous experiments demonstrate EA's efficiency and effectiveness.

The paper offers guidance on proper EA application and future research directions.

Abstract

Due to large intra-subject and inter-subject variabilities of electroencephalogram (EEG) signals, EEG-based brain-computer interfaces (BCIs) usually need subject-specific calibration to tailor the decoding algorithm for each new subject, which is time-consuming and user-unfriendly, hindering their real-world applications. Transfer learning (TL) has been extensively used to expedite the calibration, by making use of EEG data from other subjects/sessions. An important consideration in TL for EEG-based BCIs is to reduce the data distribution discrepancies among different subjects/sessions, to avoid negative transfer. Euclidean alignment (EA) was proposed in 2020 to address this challenge. Numerous experiments from 13 different BCI paradigms demonstrated its effectiveness and efficiency. This paper revisits EA, explaining its procedure and correct usage, introducing its applications and extensions, and pointing out potential new research directions. It should be very helpful to BCI researchers, especially those who are working on EEG signal decoding.