Skip to main content

Table 5 Classification performance in the larger graph dataset (mean \(\pm\) std)

From: GAT-LI: a graph attention network based learning and interpreting method for functional brain network classification

Model Accuracy Sensitivity Specificity F1 AUC MCC
SVM 0.9242 ± 0.0114 0.9235 ± 0.0133 0.9249 ± 0.0129 0.9247 ± 0.0113 0.9242 ± 0.0114 0.8485 ± 0.0228
RF 0.5975 ± 0.0127 0.6367 ± 0.0210 0.5541 ± 0.0094 0.6133 ± 0.0151 0.5954 ± 0.0127 0.1916 ± 0.0257
CNN 0.5917 ± 0.0172 0.6714 ± 0.0383 0.5160 ± 0.0394 0.5559 ± 0.1888 0.5911 ± 0.0017 0.3018 ± 0.0259
GAT2 0.9518 ± 0.0121 0.9568 ± 0.0344 0.9466 ± 0.0059 0.9526 ± 0.0099 0.9517 ± 0.0123 0.9978 ± 0.0006
  1. The bold means it is the best result for each metric (column of the table)