Comparison with other GNN methods
(A) ROCs comparison of different models on the SRPBS dataset.
(B) Histogram comparing the results of the proposed model and the SOTA models across various evaluation metrics in the SRPBS dataset. The histogram displays the mean performance metrics for each model, with error bars denoting the standard error of the mean.
(C) ROCs comparison of different models on the REST-meta-MDD dataset.
(D) Histogram comparing the results of the proposed model and the SOTA models across various evaluation metrics on the REST-meta-MDD dataset. The histogram displays the mean performance metrics for each model, with error bars denoting the standard error of the mean.
(E) t-SNE plots of the embeddings generated by each layer of the MS-GCN block.