EEG-GNN: Graph Neural Networks for Classification of Electroencephalogram (EEG) Signals

TL;DR

This paper introduces EEG-GNN, a graph neural network framework that models neural connectivity in EEG data, outperforming CNNs in classification tasks and enhancing interpretability and channel selection for EEG analysis.

Contribution

The paper develops novel GNN models tailored for EEG data, capturing neural connectivity and improving classification accuracy over traditional CNN approaches.

Findings

GNN models outperform CNNs on ErrP and RSVP datasets.

The framework enhances interpretability of EEG classification.

It facilitates EEG channel selection for reduced computational cost.

Abstract

Convolutional neural networks (CNN) have been frequently used to extract subject-invariant features from electroencephalogram (EEG) for classification tasks. This approach holds the underlying assumption that electrodes are equidistant analogous to pixels of an image and hence fails to explore/exploit the complex functional neural connectivity between different electrode sites. We overcome this limitation by tailoring the concepts of convolution and pooling applied to 2D grid-like inputs for the functional network of electrode sites. Furthermore, we develop various graph neural network (GNN) models that project electrodes onto the nodes of a graph, where the node features are represented as EEG channel samples collected over a trial, and nodes can be connected by weighted/unweighted edges according to a flexible policy formulated by a neuroscientist. The empirical evaluations show that our proposed GNN-based framework outperforms standard CNN classifiers across ErrP, and RSVP datasets, as well as allowing neuroscientific interpretability and explainability to deep learning methods tailored to EEG related classification problems. Another practical advantage of our GNN-based framework is that it can be used in EEG channel selection, which is critical for reducing computational cost, and designing portable EEG headsets.