Atoms of Thought: Universal EEG Representation Learning with Microstates
For researchers in neuroinformatics and BCI, this provides a simple yet effective representation that generalizes across tasks, though the approach is incremental (applying known microstate concept to representation learning).
The paper proposes using EEG microstates as a universal representation for EEG signals, outperforming traditional time- and frequency-domain features across sleep staging, emotion recognition, and motor imagery tasks, with improved interpretability and scalability.
Learning universal representations from electroencephalogram (EEG) signals is a cutting-edge approach in the field of neuroinformatics and brain-computer interfaces (BCIs). Conventionally, EEG is treated as a multivariate temporal signal, where time- or frequency-domain features are extracted for representation learning. This paper investigates a simple yet effective EEG representation, i.e., microstates. Microstates represent the building blocks of brain activity patterns at a microscopic time scale. We build a universal microstate tokenizer from a large medical EEG dataset by clustering continuous EEG signals into sequences of discrete microstates. The microstate tokenizer is then adopted universally across a series of downstream tasks, including sleep staging, emotion recognition, and motor imagery classification. Experimental results show that EEG representation learning with microstates outperforms traditional time-domain and frequency-domain features under different models and across different tasks. Further analysis shows that microstates offer greater interpretability and scalability, thereby opening up applications in both cognitive neuroscience and clinical research.