Backpropagation-Free Test-Time Adaptation for Lightweight EEG-Based Brain-Computer Interfaces

TL;DR

This paper introduces BFT, a novel test-time adaptation method for EEG-based BCIs that avoids backpropagation, reducing computational costs and privacy risks, while improving robustness and efficiency in real-world applications.

Contribution

The paper proposes Backpropagation-Free Transformations (BFT), a new TTA approach that eliminates backpropagation, enabling lightweight, privacy-preserving EEG decoding adaptable to resource-limited devices.

Findings

BFT achieves superior robustness across five EEG datasets.

It significantly reduces computational overhead compared to traditional methods.

BFT enhances real-world applicability of EEG-based BCIs.

Abstract

Electroencephalogram (EEG)-based brain-computer interfaces (BCIs) face significant deployment challenges due to inter-subject variability, signal non-stationarity, and computational constraints. While test-time adaptation (TTA) mitigates distribution shifts under online data streams without per-use calibration sessions, existing TTA approaches heavily rely on explicitly defined loss objectives that require backpropagation for updating model parameters, which incurs computational overhead, privacy risks, and sensitivity to noisy data streams. This paper proposes Backpropagation-Free Transformations (BFT), a TTA approach for EEG decoding that eliminates such issues. BFT applies multiple sample-wise transformations of knowledge-guided augmentations or approximate Bayesian inference to each test trial, generating multiple prediction scores for a single test sample. A learning-to-rank module enhances the weighting of these predictions, enabling robust aggregation for uncertainty suppression during inference under theoretical justifications. Extensive experiments on five EEG datasets of motor imagery classification and driver drowsiness regression tasks demonstrate the effectiveness, versatility, robustness, and efficiency of BFT. This research enables lightweight plug-and-play BCIs on resource-constrained devices, broadening the real-world deployment of decoding algorithms for EEG-based BCI.