EEG-GNN: Graph Neural Networks for Classification of Electroencephalogram (EEG) Signals
This work addresses the need for more accurate and interpretable deep learning methods for EEG signal classification, which is crucial for applications in brain-computer interfaces and neuroscience, though it is incremental as it adapts existing GNN concepts to a specific domain.
The authors tackled the problem of classifying EEG signals by overcoming the limitations of CNNs that assume equidistant electrodes, proposing a GNN-based framework that projects electrodes onto graph nodes and connects them based on functional neural connectivity. The result is that their framework outperforms standard CNN classifiers on ErrP and RSVP datasets, while also enabling neuroscientific interpretability and practical applications like EEG channel selection.
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.