cs.AINov 9, 2026

CABrain: A Correlation-Aware Brain Foundation Model for EEG Decoding

Authors: SuGil Choi, Mooseop Kim, Chi Yoon Jeong

Organizations: Electronics and Telecommunications Research Institute, 218 Gajeong-ro, Yuseong-gu, 34129, Daejeon, KOREA

Abstract

Electroencephalography (EEG) foundation models have emerged as promising paradigms for decoding brain activity through large-scale self-supervised pretraining. Notably, most existing approaches employ masked patch reconstruction, in which randomly selected EEG patches are masked and recovered by the network. However, purely random masking may limit representation learning as informative patches from highly correlated channels often remain unmasked, causing the network to underutilize weakly correlated channels or serial dependencies. Furthermore, because these models are typically based on transformer architectures, their performance is influenced by the choice of positional encoding. Although positional encoding has been extensively explored in natural language processing and computer vision, few studies have adapted it to the unique characteristics of EEG signals. To address these limitations, this study introduces a conditional positional encoding method based on graph convolutional networks (GCNs) to explicitly model inter-channel correlations, along with an adaptive masking strategy that enhances representation learning by modulating the difficulty of masked patch reconstruction. To the best of our knowledge, this is the first study to integrate graph-based representations into conditional positional encoding and introduce adaptive masking within EEG foundation model pretraining. Experimental results on ten benchmark datasets demonstrate that the proposed GCN-based positional encoding and adaptive masking strategies, both individually and in combination, achieve state-of-the-art or competitive performance, highlighting their effectiveness in EEG foundation modeling.

Figures & tables

Explore similar work

CardsList
  1. Benchmarking Positional Encoding Strategies for Transformer-Based EEG Foundation Models

    May 28, 2026Ayse Betul Yuce, Sebastian StoberMI ClassificationEEG Decoding

  2. What masking geometry works best for EEG foundation models?

    Sep 27, 2026Pierre Guetschel, Bruno Aristimunha, Yassine El Ouahidi +3Masked AutoencodersEEG Decoding

  3. DARE-EEG: A Foundation Model for Mining Dual-Aligned Representation of EEG

    May 18, 2026Yang Shao, Peiliang Gong, Qun Dai +1Masked AutoencodersSelf-Supervised Pre-Training