THD-BAR: Topology Hierarchical Derived Brain Autoregressive Modeling for EEG Generic Representations

Yang Li (Beihang University) · Wenchao Yang (Beihang University) · Weidong Yan (Beijing University of Aeronautics and Astronautics) · Wenkang Liu (Beijing University of Aeronautics and Astronautics) · Yulan Ma (Beijing University of Aeronautics and Astronautics)

autoregressive frameworksbrain topology hierarchydynamic spatial topologyeeg representationsenhanced brain autoregressive modulegeneralization capabilitiesmulti-scale spatial ordermulti-scale tokenizationnext-scale-time predictionphysiological characteristicsspatial and temporal dynamicsspecialized masking strategiestemporal sequencingtopology hierarchical derived brain autoregressive modelingtopology-hierarchical vector quantized-variational autoencoder

Large-scale pre-trained models hold significant potential for learning universal EEG representations. However, most existing methods, particularly autoregressive (AR) frameworks, primarily rely on straightforward temporal sequencing of multi-channel EEG data, which fails to capture the rich physiological characteristics inherent to EEG signals. Moreover, their time-centered modeling approach also limits the effective representation of the dynamic spatial topology of brain activity. To address these challenges and fully exploit the potential of large-scale EEG models, we propose a novel Topology Hierarchical Derived Brain Autoregressive Modeling (THD-BAR) for EEG generic representations. The core innovation of THD-BAR lies in the introduction of the Brain Topology Hierarchy (BTH), which establishes a multi-scale spatial order for EEG channels. This hierarchical structure enables a redefinition of autoregressive learning as a "next-scale-time prediction" problem, effectively capturing both spatial and temporal dynamics. Based on BTH, we design a Topology-Hierarchical Vector Quantized-Variational Autoencoder (THVQ-VAE) for multi-scale tokenization and develop an enhanced Brain Autoregressive (BAR) module with specialized masking strategies for prediction. Through extensive large-scale pre-training on 17 datasets, followed by rigorous validation on 10 downstream datasets spanning 5 distinct tasks, THD-BAR consistently outperforms existing methods. These results highlight the superior generalization and modeling capabilities of our proposed approach.