When and How to Adapt: Subject Shifts Detection and Prototype-Guided Correction for Online EEG Decoding
TL;DR
A novel Prototype-driven online EEG Decoding framework (PRED) that incorporates a Subject Shift Detector based on policy stability to reliably identify latent domain shifts unsupervisedly, thereby constructing adaptive soft boundaries and a Prototype-guided Shift Correction mechanism that leverages a multi-granular memory structure to guide distribution alignment while preserving semantic stability.
Abstract
Online EEG decoding is pivotal for real-world Brain-Computer Interfaces (BCIs) but confronts significant challenges arising from continuous distribution shifts, including both inter- and intra-subject variations. Existing Unsupervised Continual Domain Adaptation (UCDA) methods typically rely on rigid hard boundaries such as subject switch labels or fixed batch sizes to trigger adaptation. Meanwhile, some online EEG decoding methods that utilize detected shifts as soft boundaries are ill-suited for unsupervised scenarios and lack effective distribution alignment strategies. To address these issues, we propose a novel Prototype-driven online EEG Decoding framework (PRED). PRED incorporates a Subject Shift Detector (SSD) based on policy stability to reliably identify latent domain shifts unsupervisedly, thereby constructing adaptive soft boundaries. Furthermore, we design a Prototype-guided Shift Correction (PSC) mechanism that leverages a multi-granular memory structure to guide distribution alignment while preserving semantic stability. Experiments on three public datasets confirm that PRED achieves superior plasticity and stability, and demonstrates significant futurity, i.e., the capability of forward transfer to a subject's future samples.