DIVER-0 : A Fully Channel Equivariant EEG Foundation Model

TL;DR

DIVER-0 is a novel EEG foundation model that leverages full spatio-temporal attention and equivariant positional encoding to improve generalization across diverse electrode configurations with limited pretraining data.

Contribution

It introduces a fully channel and temporal equivariant attention-based architecture with STCPE for robust EEG modeling across varied electrode setups.

Findings

Achieves competitive performance with only 10% of pretraining data.

Maintains consistent results across all channel permutation conditions.

Demonstrates strong cross-dataset generalization.

Abstract

Electroencephalography (EEG) is a non-invasive technique widely used in brain-computer interfaces and clinical applications, yet existing EEG foundation models face limitations in modeling spatio-temporal brain dynamics and lack channel permutation equivariance, preventing robust generalization across diverse electrode configurations. To address these challenges, we propose DIVER-0, a novel EEG foundation model that demonstrates how full spatio-temporal attention-rather than segregated spatial or temporal processing-achieves superior performance when properly designed with Rotary Position Embedding (RoPE) for temporal relationships and binary attention biases for channel differentiation. We also introduce Sliding Temporal Conditional Positional Encoding (STCPE), which improves upon existing conditional positional encoding approaches by maintaining both temporal translation equivariance and channel permutation equivariance, enabling robust adaptation to arbitrary electrode configurations unseen during pretraining. Experimental results demonstrate that DIVER-0 achieves competitive performance with only 10% of pretraining data while maintaining consistent results across all channel permutation conditions, validating its effectiveness for cross-dataset generalization and establishing key design principles for handling the inherent heterogeneity of neural recording setups.