Table 7 Performance on medium-sized data.
From: Fraud detection and explanation in medical claims using GNN architectures
Model | Architecture | Node Emb. Dim. | Performance | Time (min.) | |||
|---|---|---|---|---|---|---|---|
(Homogeneous/ Heterogeneous) | Macro-F1 | Accuracy | Preprocessing | Training | Inference | ||
HINormer | Heterogeneous | 128 | 0.81 | 0.81 | 227.28 | 0.63 | 0.02 |
HybridGNN | Heterogeneous | 256 | 0.58 | 0.61 | 1887.67 | 12.41 | 1.25 |
RE-GraphSAGE | Homogeneous | 128 | 0.84 | 0.84 | 7.08 | 0.16 | 0.03 |
