Graph Classification On Re M12K
Metriken
Accuracy
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
| Paper Title | ||
|---|---|---|
| GFN-light | 49.75% | Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification |
| GFN | 49.43% | Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification |
| 2D CNN | 48.13% | Graph Classification with 2D Convolutional Neural Networks |
| WEGL | 47.8% | Wasserstein Embedding for Graph Learning |
| CapsGNN | 46.62% | Capsule Graph Neural Network |
| DGK | 32.22% | Deep Graph Kernels |
0 of 6 row(s) selected.