Node Classification On Cluster
평가 지표
Accuracy
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | Accuracy | Paper Title | Repository |
|---|---|---|---|
| GatedGCN-PE | 76.08 | Benchmarking Graph Neural Networks | |
| Exphormer | 78.22±0.045 | Exphormer: Sparse Transformers for Graphs | |
| GRIT | 80.026 | Graph Inductive Biases in Transformers without Message Passing | |
| ARGNP | 77.35 | Automatic Relation-aware Graph Network Proliferation | |
| EIGENFORMER | 77.456 | Graph Transformers without Positional Encodings | - |
| GatedGCN+ | 79.128 ± 0.235 | Can Classic GNNs Be Strong Baselines for Graph-level Tasks? Simple Architectures Meet Excellence | |
| GPS | 77.95 | Recipe for a General, Powerful, Scalable Graph Transformer | |
| GPTrans-Nano | 78.07 | Graph Propagation Transformer for Graph Representation Learning | |
| EGT | 79.232 | Global Self-Attention as a Replacement for Graph Convolution | |
| TIGT | 78.033 | Topology-Informed Graph Transformer | |
| CKGCN | 79.003 | CKGConv: General Graph Convolution with Continuous Kernels | |
| NeuralWalker | 78.189 ± 0.188 | Learning Long Range Dependencies on Graphs via Random Walks |
0 of 12 row(s) selected.