Skip to main content

Table 12 Performance of ML-GCN over the Koumbia multilayer networks with varying number of layers, and different types of input features

From: Graph convolutional and attention models for entity classification in multilayer networks

\(\ell\) Koumbia-Fon Koumbia-Foff Koumbia-normal
Accuracy MRR Accuracy MRR Accuracy MRR
2 \(\mathbf {0.8520 \pm 0.0863}\) \(\mathbf {0.9260 \pm 0.0431}\) \(0.7444 \pm 0.0172\) \(0.8722 \pm 0.0086\) \(0.7503 \pm 0.0186\) \(0.8751 \pm 0.0093\)
5 \(\mathbf {0.9370 \pm 0.0063}\) \(\mathbf {0.9685 \pm 0.0032}\) \(0.6880 \pm 0.0273\) \(0.8411 \pm 0.0136\) \(0.8163 \pm 0.0143\) \(0.9082 \pm 0.0071\)
10 \(\mathbf {0.9359 \pm 0.0085}\) \(\mathbf {0.9679 \pm 0.0043}\) \(0.6540 \pm 0.0200\) \(0.8270 \pm 0.0100\) \(0.8237 \pm 0.0157\) \(0.9118 \pm 0.0082\)
15 \(\mathbf {0.9358 \pm 0.0089}\) \(\mathbf {0.9679 \pm 0.0044}\) \(0.6378 \pm 0.0215\) \(0.8189 \pm 0.0108\) \(0.8238 \pm 0.0216\) \(0.9119 \pm 0.0108\)
20 \(\mathbf {0.9363 \pm 0.0067}\) \(\mathbf {0.9681 \pm 0.0033}\) \(0.6282 \pm 0.0116\) \(0.8141 \pm 0.0058\) \(0.8221 \pm 0.0153\) \(0.9111 \pm 0.0077\)
  1. Bold values correspond to best performances