Node Classification On Pattern
평가 지표
Accuracy
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | Accuracy | Paper Title | Repository |
|---|---|---|---|
| Exphormer | 86.74 | Exphormer: Sparse Transformers for Graphs | |
| NeuralWalker | 86.977 ± 0.012 | Learning Long Range Dependencies on Graphs via Random Walks | |
| GRIT | 87.196 | Graph Inductive Biases in Transformers without Message Passing | |
| EIGENFORMER | 86.738 | Graph Transformers without Positional Encodings | - |
| GPTrans-Nano | 86.734±0.008 | Graph Propagation Transformer for Graph Representation Learning | |
| GatedGCN+ | 87.029 ± 0.037 | Can Classic GNNs Be Strong Baselines for Graph-level Tasks? Simple Architectures Meet Excellence | |
| GatedGCN | 86.508 | Benchmarking Graph Neural Networks | |
| EGT | 86.821 | Global Self-Attention as a Replacement for Graph Convolution | |
| CKGCN | 88.661 | CKGConv: General Graph Convolution with Continuous Kernels | |
| TIGT | 86.680 | Topology-Informed Graph Transformer | |
| GPS | 86.685 | Recipe for a General, Powerful, Scalable Graph Transformer |
0 of 11 row(s) selected.