Prototype-Guided Non-Exemplar Continual Learning for Cross-subject EEG Decoding

TL;DR

This paper introduces ProNECL, a novel continual learning framework for EEG decoding that preserves knowledge across subjects without storing historical data, using prototypes for efficient representation and alignment.

Contribution

ProNECL is the first method to use prototype-based regularization for privacy-preserving continual EEG decoding across subjects.

Findings

ProNECL outperforms existing methods on BCI datasets.

It effectively balances knowledge retention and adaptability.

ProNECL does not require storing historical EEG samples.

Abstract

Due to the significant variability in electroencephalo-gram (EEG) signals across individuals, knowledge acquired from previous subjects is often overwritten as new subjects are introduced in continual EEG decoding tasks. Existing methods mainly rely on storing historical data from seen subjects as replay buffers to mitigate forgetting, which is impractical under privacy or memory constraints. To address this issue, we propose a Prototype-guided Non-Exemplar Continual Learning (ProNECL) framework that preserves prior knowledge without accessing historical EEG samples. ProNECL summarizes subject-specific discriminative representations into class-level prototypes and incrementally aligns new subject representations with a global prototype memory through prototype-based feature regulariza-tion and cross-subject alignment. Experiments on the BCI Com-petition IV 2a and 2b datasets demonstrate that ProNECL effec-tively balances knowledge retention and adaptability, achieving superior performance in cross-subject continual EEG decoding tasks.