Node Classification On Non Homophilic 6
Metrics
1:1 Accuracy
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | 1:1 Accuracy |
|---|---|
| simplifying-graph-convolutional-networks | 59.73±0.12 |
| revisiting-heterophily-for-graph-neural | 67.4±0.44 |
| graph-attention-networks | 61.09±0.77 |
| revisiting-heterophily-for-graph-neural | 67.15±0.41 |
| simple-and-deep-graph-convolutional-networks-1 | 66.38±0.45 |
| revisiting-heterophily-for-graph-neural | 67.01±0.38 |
| combining-label-propagation-and-simple-models-1 | 64.52±0.62 |
| generalizing-graph-neural-networks-beyond | 67.22±0.90 |
| new-benchmarks-for-learning-on-non | 60.99±0.14 |
| semi-supervised-classification-with-graph | 62.23±0.53 |
| new-benchmarks-for-learning-on-non | 57.71±0.36 |
| revisiting-heterophily-for-graph-neural | 67.3±0.48 |
| revisiting-heterophily-for-graph-neural | 67.44±0.31 |
| mixhop-higher-order-graph-convolution | 66.80±0.58 |
| beyond-low-frequency-information-in-graph | 66.86±0.53 |
| revisiting-heterophily-for-graph-neural | 66.53±0.57 |
| new-benchmarks-for-learning-on-non | 56.96±0.26 |
| new-benchmarks-for-learning-on-non | 59.66±0.92 |
| predict-then-propagate-graph-neural-networks | 67.21±0.56 |
| revisiting-heterophily-for-graph-neural | 66.39±0.56 |
| simple-and-deep-graph-convolutional-networks-1 | 66.42±0.56 |
| revisiting-heterophily-for-graph-neural | 66.6±0.57 |
| revisiting-heterophily-for-graph-neural | 66.67±0.56 |
| joint-adaptive-feature-smoothing-and-topology | 66.90±0.50 |
| revisiting-heterophily-for-graph-neural | 67.5±0.53 |
| combining-label-propagation-and-simple-models-1 | 64.60±0.57 |
| new-benchmarks-for-learning-on-non | 66.55±0.72 |
| new-benchmarks-for-learning-on-non | 56.50±0.41 |