Table 5 F1-score of Ensemble GNN models for different number of base classifiers for the CRC dataset
From: Automatic disease prediction from human gut metagenomic data using boosting GraphSAGE
Number of base classifiers | Boosting GraphSAGE | Bagging GraphSAGE | Boosting GCN | Bagging GCN |
|---|---|---|---|---|
5 | 0.82 | 0.83 | 0.76 | 0.75 |
10 | 0.83 | 0.85 | 0.76 | 0.81 |
15 | 0.87 | 0.85 | 0.81 | 0.82 |
20 | 0.85 | 0.86 | 0.82 | 0.8 |
25 | 0.8 | 0.86 | 0.8 | 0.84 |
30 | 0.85 | 0.85 | 0.84 | 0.82 |
35 | 0.85 | 0.83 | 0.82 | 0.81 |
40 | 0.83 | 0.82 | 0.81 | 0.81 |