Node Classification On Cornell
المقاييس
Accuracy
النتائج
نتائج أداء النماذج المختلفة على هذا المعيار القياسي
جدول المقارنة
| اسم النموذج | Accuracy |
|---|---|
| diffwire-inductive-graph-rewiring-via-the | 69.04 |
| revisiting-heterophily-for-graph-neural | 85.68 ± 5.8 |
| graph-neural-reaction-diffusion-models | 92.72 ± 5.88 |
| neural-sheaf-diffusion-a-topological | 85.68 ± 6.51 |
| self-attention-dual-embedding-for-graphs-with | 86.21±5.59 |
| geom-gcn-geometric-graph-convolutional-1 | 56.76 |
| heterophilic-graph-neural-networks | 68.23±2.90 |
| unig-encoder-a-universal-feature-encoder-for | 86.75±6.56 |
| geom-gcn-geometric-graph-convolutional-1 | 55.68 |
| beyond-homophily-structure-aware-path | - |
| finding-global-homophily-in-graph-neural | 83.51±4.26 |
| generalizing-graph-neural-networks-beyond | 78.11 ± 6.68 |
| revisiting-heterophily-for-graph-neural | 82.43 ± 5.44 |
| joint-adaptive-feature-smoothing-and-topology | 78.11 ± 6.55 |
| deltagnn-graph-neural-network-with | 75.67±1.91 |
| revisiting-heterophily-for-graph-neural | 82.43 ± 5.44 |
| revisiting-heterophily-for-graph-neural | 85.95 ± 5.64 |
| graph-neural-aggregation-diffusion-with | 83.3±7.0 |
| cn-motifs-perceptive-graph-neural-networks | 82.38 ± 6.13 |
| revisiting-heterophily-for-graph-neural | 86.49 ± 6.73 |
| refining-latent-homophilic-structures-over | 85.96±5.1 |
| fdgatii-fast-dynamic-graph-attention-with | 82.4324 |
| neural-sheaf-diffusion-a-topological | 84.86 ± 4.71 |
| ordered-gnn-ordering-message-passing-to-deal | 87.03±4.73 |
| tree-decomposed-graph-neural-network | 82.92 ± 6.61 (0, 2-6) |
| large-scale-learning-on-non-homophilous | 77.84 ± 5.81 |
| beyond-low-frequency-information-in-graph | 76.76 ± 5.87 |
| two-sides-of-the-same-coin-heterophily-and | 85.68 ± 6.63 |
| breaking-the-entanglement-of-homophily-and | 82.9±3.0 |
| graphrare-reinforcement-learning-enhanced | 87.84±4.05 |
| finding-global-homophily-in-graph-neural | 85.95±5.10 |
| the-heterophilic-snowflake-hypothesis | 68.18 |
| revisiting-heterophily-for-graph-neural | 85.14 ± 6.07 |
| transitivity-preserving-graph-representation | 70.0 ±4.44 |
| diffwire-inductive-graph-rewiring-via-the | 58.02 |
| unigap-a-universal-and-adaptive-graph | 84.96 ± 5.0 |
| generalizing-graph-neural-networks-beyond | 79.46 ± 4.80 |
| diffusion-jump-gnns-homophiliation-via | 87.03±1.62 |
| simple-and-deep-graph-convolutional-networks-1 | 77.86 ± 3.79 |
| non-local-graph-neural-networks | 54.7 ± 7.6 |
| gcnh-a-simple-method-for-representation | 86.49±6.98 |
| sign-is-not-a-remedy-multiset-to-multiset | 86.48 ± 6.1 |
| non-local-graph-neural-networks | 84.9 ± 5.7 |
| improving-graph-neural-networks-with-simple | 87.84±6.19 |
| cat-a-causally-graph-attention-network-for | 88.8±2.1 |
| universal-deep-gnns-rethinking-residual | 84.32±7.29 |
| breaking-the-limit-of-graph-neural-networks | 81.62 ± 3.90 |
| understanding-over-squashing-and-bottlenecks-1 | - |
| learn-from-heterophily-heterophilous | 80.00 ± 4.26 |
| make-heterophily-graphs-better-fit-gnn-a | 82.88±5.56 |
| geom-gcn-geometric-graph-convolutional-1 | 60.81 |
| neural-sheaf-diffusion-a-topological | 86.49 ± 7.35 |
| beyond-homophily-with-graph-echo-state-1 | 81.1±6.0 |
| sheaf-neural-networks-with-connection | 85.95±7.72 |
| revisiting-heterophily-for-graph-neural | 85.68 ± 4.84 |
| transfer-entropy-in-graph-convolutional | 85.68 ± 6.63 |
| simple-truncated-svd-based-model-for-node | 84.05±4.67 |
| mixhop-higher-order-graph-convolution | 73.51 ± 6.34 |
| non-local-graph-neural-networks | 57.6 ± 5.5 |
| revisiting-heterophily-for-graph-neural | 85.41 ± 5.3 |