Graph Classification On Cifar10 100K
Metrics
Accuracy (%)
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Accuracy (%) |
|---|---|
| graph-attention-networks | 65.48 |
| graph-inductive-biases-in-transformers | 76.468 |
| recurrent-distance-encoding-neural-networks | 76.853±0.185 |
| principal-neighbourhood-aggregation-for-graph | 70.47 |
| exphormer-sparse-transformers-for-graphs | 74.754±0.194 |
| masked-attention-is-all-you-need-for-graphs | 75.413±0.248 |
| inductive-representation-learning-on-large | 66.08 |
| edge-augmented-graph-transformers-global-self | 68.702 |
| geometric-deep-learning-on-graphs-and | 53.42 |
| benchmarking-graph-neural-networks | 67.312 |
| transformers-for-capturing-multi-level-graph | 76.180±0.277 |
| graph-transformers-without-positional | 70.194 |
| automatic-relation-aware-graph-network | 73.90 |
| how-powerful-are-graph-neural-networks | 53.28 |
| unlocking-the-potential-of-classic-gnns-for | 77.218 ± 0.381 |
| topology-informed-graph-transformer | 73.955 |
| learning-long-range-dependencies-on-graphs | 80.027 ± 0.185 |
| residual-gated-graph-convnets | 69.37 |
| recipe-for-a-general-powerful-scalable-graph | 72.298 |
| directional-graph-networks-1 | 72.84 |