Node Classification On Wisconsin
المقاييس
Accuracy
النتائج
نتائج أداء النماذج المختلفة على هذا المعيار القياسي
جدول المقارنة
| اسم النموذج | Accuracy |
|---|---|
| heterophilous-distribution-propagation-for | 88.82 ± 3.40 |
| beyond-low-frequency-information-in-graph | 79.61 ± 1.58 |
| neural-sheaf-diffusion-a-topological | 89.21 ± 3.84 |
| graphrare-reinforcement-learning-enhanced | 90.00±2.97 |
| revisiting-heterophily-for-graph-neural | 88.43 ± 2.39 |
| refining-latent-homophilic-structures-over | 88.32±2.3 |
| generalizing-graph-neural-networks-beyond | 84.31 ± 3.70 |
| finding-global-homophily-in-graph-neural | 87.06±3.53 |
| finding-global-homophily-in-graph-neural | 88.04±3.22 |
| sign-is-not-a-remedy-multiset-to-multiset | 89.01 ± 4.1 |
| non-local-graph-neural-networks | 56.9 ± 7.3 |
| revisiting-heterophily-for-graph-neural | 86.47 ± 3.77 |
| gcnh-a-simple-method-for-representation | - |
| diffusion-jump-gnns-homophiliation-via | - |
| revisiting-heterophily-for-graph-neural | 86.47 ± 3.77 |
| transfer-entropy-in-graph-convolutional | 87.45 ± 3.70 |
| geom-gcn-geometric-graph-convolutional-1 | 58.24 |
| improving-graph-neural-networks-with-simple | 88.43±3.22 |
| unigap-a-universal-and-adaptive-graph | 87.73 ± 4.8 |
| large-scale-learning-on-non-homophilous | 75.49 ± 5.72 |
| learn-from-heterophily-heterophilous | 85.88 ± 3.18 |
| cat-a-causally-graph-attention-network-for | 85.6±2.1 |
| understanding-over-squashing-and-bottlenecks-1 | 55.51±0.27 |
| label-wise-message-passing-graph-neural | 86.9±2.2 |
| beyond-low-frequency-information-in-graph | 86.98 ± 3.78 |
| diffwire-inductive-graph-rewiring-via-the | 79.05 |
| revisiting-heterophily-for-graph-neural | 87.45 ± 3.74 |
| graph-neural-reaction-diffusion-models | 93.72 ± 4.59 |
| revisiting-heterophily-for-graph-neural | 88.04 ± 3.66 |
| neural-sheaf-diffusion-a-topological | 88.63 ± 2.75 |
| revisiting-heterophily-for-graph-neural | 88.43 ± 3.22 |
| the-heterophilic-snowflake-hypothesis | 88.77 |
| revisiting-heterophily-for-graph-neural | 88.43 ± 3.66 |
| mamba-based-graph-convolutional-networks | 86.27±2.16 |
| sheaf-neural-networks-with-connection | 88.73±4.47 |
| improving-graph-neural-networks-by-learning | 87.84±3.70 |
| beyond-homophily-with-graph-echo-state-1 | 83.3±3.8 |
| neural-sheaf-diffusion-a-topological | 89.41 ± 4.74 |
| higher-order-graph-convolutional-network-with | 94.99±0.65 |
| non-local-graph-neural-networks | 87.3 ± 4.3 |
| tree-decomposed-graph-neural-network | 85.57 ± 3.78 (0, 3-5) |
| revisiting-heterophily-for-graph-neural | 88.24 ± 3.16 |
| geom-gcn-geometric-graph-convolutional-1 | 64.12 |
| ordered-gnn-ordering-message-passing-to-deal | 88.04±3.63 |
| breaking-the-entanglement-of-homophily-and | 81.6±3.5 |
| self-attention-dual-embedding-for-graphs-with | 88.63±4.54 |
| deltagnn-graph-neural-network-with | 80.00±0.88 |
| universal-deep-gnns-rethinking-residual | 87.64±3.74 |
| fdgatii-fast-dynamic-graph-attention-with | 86.2745 |
| graph-neural-aggregation-diffusion-with | 87.7±3.7 |
| simple-truncated-svd-based-model-for-node | 86.67±4.22 |
| cn-motifs-perceptive-graph-neural-networks | 86.63 ± 3.57 |
| joint-adaptive-feature-smoothing-and-topology | 82.55 ± 6.23 |
| transitivity-preserving-graph-representation | 81.6 ±8.24 |
| make-heterophily-graphs-better-fit-gnn-a | 85.01±5.51 |
| geom-gcn-geometric-graph-convolutional-1 | 56.67 |
| non-local-graph-neural-networks | 60.2 ± 5.3 |
| simple-and-deep-graph-convolutional-networks-1 | 80.39 ± 3.40 |
| diffwire-inductive-graph-rewiring-via-the | 69.25 |
| two-sides-of-the-same-coin-heterophily-and | 86.86 ± 3.29 |
| unig-encoder-a-universal-feature-encoder-for | 88.03±4.42 |
| generalizing-graph-neural-networks-beyond | 83.14 ± 4.26 |
| mixhop-higher-order-graph-convolution | 75.88 ± 4.90 |