Brain-token learning improves modeling of long-term brainwave patterns
Brain-Token Learning: Microstate-Based Tokenization and Multi-Scale Interaction for Long-Horizon EEG Sequence Modeling
Artificial Intelligence
Summary
Modeling brain activity over long periods is hard because brain signals are complex and change a lot between people. The authors introduced Brain-Token Learning, a method that breaks brain signals into meaningful chunks called brain tokens based on natural brain states instead of fixed time parts. These tokens capture stable brain activity patterns and how they shift over time. This approach works better than previous methods in understanding brainwaves across multiple datasets and conditions.
What this means in practice
- •For clinical neuroimaging teams: Improve the analysis of long EEG recordings to detect and interpret brain state changes in clinical conditions.
- •For affective computing developers: Enhance emotion recognition systems by using brain-token sequences that better reflect brain activity dynamics over time.
Authors
Weishan Ye, Yue Pan, Li Zhang, Gan Huang, Zhen Liang
Abstract
Electroencephalography (EEG) provides a non-invasive window into dynamic brain activity, yet modeling long-horizon EEG sequences remains challenging due to their high temporal complexity, substantial variability across subjects, and the lack of biologically meaningful sequence representations. Existing tokenization strategies, such as fixed-window and patch-based representations, discretize EEG signals according to artificial temporal boundaries, which may disrupt intrinsic brain-state dynamics. In this work, we propose Brain-Token Learning, a neuroscience-inspired framework that introduces Brain Tokenization for long-horizon EEG sequence modeling. Instead of partitioning EEG signals into predefined temporal segments, Brain Tokenization represents EEG as sequences of recurrent microstate-derived brain tokens, where each token corresponds to a quasi-stable large-scale brain state with variable temporal duration. Based on these biologically grounded tokens, we further develop a multi-scale token interaction module consisting of Latent State Aggregation and State Transition Modeling to jointly capture global brain-state context and local microstate transitions. We evaluate Brain-Token on five heterogeneous EEG datasets, including the newly collected long-horizon NeuroLong dataset and four affective or clinical EEG datasets (SEED, DEAP, MDD, and NSSI). Extensive experiments demonstrate that Brain-Token consistently outperforms conventional CNN/LSTM architectures, Transformer-based models, and domain adaptation methods across diverse EEG scenarios. Further analysis verifies the effectiveness of microstate-based tokenization and multi-scale interaction for learning robust and interpretable EEG representations. These results establish Brain-Token as a biologically grounded tokenization paradigm for long-horizon EEG sequence modeling.