EEGReXferNet: A Lightweight Gen-AI Framework for EEG Subspace Reconstruction via Cross-Subject Transfer Learning and Channel-Aware Embedding

TL;DR

EEGReXferNet is a lightweight, cross-subject transfer learning framework that enhances EEG signal reconstruction by integrating spatial, spectral, and temporal features, enabling real-time artifact removal and improved BCI performance.

Contribution

The paper introduces EEGReXferNet, a novel modular deep learning framework that combines transfer learning, channel-aware embedding, and spectral encoding for efficient EEG reconstruction.

Findings

Achieves high spatial-temporal-spectral resolution (mean PSD correlation >= 0.95)

Reduces model weights by approximately 45% to prevent overfitting

Maintains computational efficiency suitable for real-time EEG processing

Abstract

Electroencephalography (EEG) is a widely used non-invasive technique for monitoring brain activity, but low signal-to-noise ratios (SNR) due to various artifacts often compromise its utility. Conventional artifact removal methods require manual intervention or risk suppressing critical neural features during filtering/reconstruction. Recent advances in generative models, including Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs), have shown promise for EEG reconstruction; however, these approaches often lack integrated temporal-spectral-spatial sensitivity and are computationally intensive, limiting their suitability for real-time applications like brain-computer interfaces (BCIs). To overcome these challenges, we introduce EEGReXferNet, a lightweight Gen-AI framework for EEG subspace reconstruction via cross-subject transfer learning - developed using Keras TensorFlow (v2.15.1). EEGReXferNet employs a modular architecture that leverages volume conduction across neighboring channels, band-specific convolution encoding, and dynamic latent feature extraction through sliding windows. By integrating reference-based scaling, the framework ensures continuity across successive windows and generalizes effectively across subjects. This design improves spatial-temporal-spectral resolution (mean PSD correlation >= 0.95; mean spectrogram RV-Coefficient >= 0.85), reduces total weights by ~45% to mitigate overfitting, and maintains computational efficiency for robust, real-time EEG preprocessing in neurophysiological and BCI applications.