Node Classification On Squirrel
المقاييس
Accuracy
النتائج
نتائج أداء النماذج المختلفة على هذا المعيار القياسي
جدول المقارنة
| اسم النموذج | Accuracy |
|---|---|
| improving-graph-neural-networks-by-learning | 75.32±1.82 |
| mixhop-higher-order-graph-convolution | 43.80 ± 1.48 |
| revisiting-heterophily-for-graph-neural | 67.4 ± 2.21 |
| sheaf-neural-networks-with-connection | 45.19±1.57 |
| breaking-the-limit-of-graph-neural-networks | 48.85 ± 0.78 |
| heterophilic-graph-neural-networks | 39.78±0.91 |
| ordered-gnn-ordering-message-passing-to-deal | 62.44±1.96 |
| cn-motifs-perceptive-graph-neural-networks | 63.60±1.96 |
| universal-deep-gnns-rethinking-residual | - |
| revisiting-heterophily-for-graph-neural | 67.07 ± 1.65 |
| the-heterophilic-snowflake-hypothesis | 57.83 |
| generalizing-graph-neural-networks-beyond | 28.98 ± 1.97 |
| holonets-spectral-convolutions-do-extend-to | 76.71±1.92 |
| finding-global-homophily-in-graph-neural | 57.54±1.39 |
| revisiting-heterophily-for-graph-neural | 40.02 ± 0.96 |
| revisiting-heterophily-for-graph-neural | 67.06 ± 1.66 |
| breaking-the-entanglement-of-homophily-and | 45.2±1.3 |
| beyond-homophily-with-graph-echo-state-1 | 71.2±1.5 |
| label-wise-message-passing-graph-neural | 62.6±1.6 |
| heterophilous-distribution-propagation-for | 62.07 ± 1.57 |
| diffusion-jump-gnns-homophiliation-via | 73.48±1.59 |
| simple-truncated-svd-based-model-for-node | 74.17±1.83 |
| cat-a-causally-graph-attention-network-for | 59.3±1.8 |
| graph-neural-reaction-diffusion-models | 65.62 ± 2.33 |
| learn-from-heterophily-heterophilous | 54.78 ± 1.58 |
| simple-and-deep-graph-convolutional-networks-1 | 38.47 ± 1.58 |
| signgt-signed-attention-based-graph | - |
| edge-directionality-improves-learning-on | 75.31±1.92 |
| joint-adaptive-feature-smoothing-and-topology | 46.31 ± 2.46 |
| generalizing-graph-neural-networks-beyond | 32.33 ± 1.94 |
| geom-gcn-geometric-graph-convolutional-1 | 38.14 |
| revisiting-heterophily-for-graph-neural | 66.98 ± 1.71 |
| revisiting-heterophily-for-graph-neural | 55.19 ± 1.49 |
| enhancing-intra-class-information-extraction | 57.32±1.89 |
| non-local-graph-neural-networks | 33.7 ± 1.5 |
| improving-graph-neural-networks-with-simple | 74.10±1.89 |
| make-heterophily-graphs-better-fit-gnn-a | 72.24±1.52 |
| geom-gcn-geometric-graph-convolutional-1 | 33.32 |
| beyond-low-frequency-information-in-graph | 30.83 ± 0.69 |
| restructuring-graph-for-higher-homophily-via | 56.3 ± 2.2 |
| neural-sheaf-diffusion-a-topological | 54.78 ± 1.81 |
| understanding-over-squashing-and-bottlenecks-1 | 37.05±0.17 |
| graphrare-reinforcement-learning-enhanced | 55.90±1.39 |
| large-scale-learning-on-non-homophilous | 61.81 ± 1.80 |
| refining-latent-homophilic-structures-over | 60.27±1.2 |
| revisiting-heterophily-for-graph-neural | 45.00 ± 1.4 |
| self-attention-dual-embedding-for-graphs-with | 68.20±1.57 |
| transfer-entropy-in-graph-convolutional | 55.04±1.64 |
| neural-sheaf-diffusion-a-topological | 53.17 ± 1.31 |
| two-sides-of-the-same-coin-heterophily-and | 55.17 ± 1.58 |
| revisiting-heterophily-for-graph-neural | 51.8 ± 1.5 |
| finding-global-homophily-in-graph-neural | 57.88±1.76– |
| transitivity-preserving-graph-representation | 66.96 ±2.49 |
| gcnh-a-simple-method-for-representation | - |
| non-local-graph-neural-networks | 56.8 ± 2.5 |
| neural-sheaf-diffusion-a-topological | 56.34 ± 1.32 |
| sign-is-not-a-remedy-multiset-to-multiset | 63.60 ± 1.7 |
| non-local-graph-neural-networks | 59.0 ± 1.2 |
| geom-gcn-geometric-graph-convolutional-1 | 36.24 |