Node Classification On Texas
المقاييس
Accuracy
النتائج
نتائج أداء النماذج المختلفة على هذا المعيار القياسي
جدول المقارنة
| اسم النموذج | Accuracy |
|---|---|
| higher-order-graph-convolutional-network-with | 92.45±0.73 |
| simple-truncated-svd-based-model-for-node | 87.57 ± 5.44 |
| the-heterophilic-snowflake-hypothesis | 93.09 |
| neural-sheaf-diffusion-a-topological | 85.67 ± 6.95 |
| two-sides-of-the-same-coin-heterophily-and | 84.86 ± 4.55 |
| mixhop-higher-order-graph-convolution | 77.84 ± 7.73 |
| revisiting-heterophily-for-graph-neural | 88.38 ± 3.64 |
| unig-encoder-a-universal-feature-encoder-for | 85.40±5.3 |
| revisiting-heterophily-for-graph-neural | 81.89 ± 4.53 |
| self-attention-dual-embedding-for-graphs-with | 86.49±5.12 |
| geom-gcn-geometric-graph-convolutional-1 | 59.73 |
| finding-global-homophily-in-graph-neural | 84.05±4.90 |
| neural-sheaf-diffusion-a-topological | 82.97 ± 5.13 |
| heterophilic-graph-neural-networks | 57.36±0.60 |
| enhancing-intra-class-information-extraction | 85.84±4.23 |
| sign-is-not-a-remedy-multiset-to-multiset | 89.19 ± 4.5 |
| deltagnn-graph-neural-network-with | 74.05±3.08 |
| large-scale-learning-on-non-homophilous | 74.60 ± 8.37 |
| non-local-graph-neural-networks | 85.4 ± 3.8 |
| improving-graph-neural-networks-with-simple | 87.30 ± 5.55 |
| neural-sheaf-diffusion-a-topological | 85.95 ± 5.51 |
| gcnh-a-simple-method-for-representation | 87.84±3.87 |
| graph-neural-aggregation-diffusion-with | 88.3±3.5 |
| learn-from-heterophily-heterophilous | 86.22 ± 4.67 |
| revisiting-heterophily-for-graph-neural | 87.84 ± 4.4 |
| cat-a-causally-graph-attention-network-for | 83.0±2.5 |
| graph-neural-reaction-diffusion-models | 94.59 ± 5.97 |
| beyond-low-frequency-information-in-graph | 76.49 ± 2.87 |
| ordered-gnn-ordering-message-passing-to-deal | 86.22±4.12 |
| diffusion-jump-gnns-homophiliation-via | 92.43±3.15 |
| transfer-entropy-in-graph-convolutional | 84.86 ± 4.55 |
| refining-latent-homophilic-structures-over | 86.32±4.5 |
| improving-graph-neural-networks-by-learning | - |
| understanding-over-squashing-and-bottlenecks-1 | 64.46±0.38 |
| bregman-graph-neural-network | 84.05 ± 5.47 |
| tree-decomposed-graph-neural-network | 83.00 ± 4.50 |
| sheaf-neural-networks-with-connection | 86.16±2.24 |
| revisiting-heterophily-for-graph-neural | 81.89 ± 4.53 |
| revisiting-heterophily-for-graph-neural | 88.11 ± 3.24 |
| simple-and-deep-graph-convolutional-networks-1 | 77.57 ± 3.83 |
| generalizing-graph-neural-networks-beyond | 83.24 ± 7.07 |
| beyond-homophily-with-graph-echo-state-1 | 84.3±4.4 |
| non-local-graph-neural-networks | 62.6 ± 7.1 |
| revisiting-heterophily-for-graph-neural | 88.38 ± 3.43 |
| cn-motifs-perceptive-graph-neural-networks | 85.68±5.28 |
| finding-global-homophily-in-graph-neural | 84.32±4.15 |
| fdgatii-fast-dynamic-graph-attention-with | 80.5405 |
| non-local-graph-neural-networks | 65.5 ± 6.6 |
| make-heterophily-graphs-better-fit-gnn-a | 84.86±5.01 |
| universal-deep-gnns-rethinking-residual | 84.60±5.32 |
| revisiting-heterophily-for-graph-neural | 88.38 ± 3.43 |
| breaking-the-entanglement-of-homophily-and | - |
| geom-gcn-geometric-graph-convolutional-1 | 67.57 |
| generalizing-graph-neural-networks-beyond | 80.00 ± 6.77 |
| breaking-the-limit-of-graph-neural-networks | 83.62 ± 5.50 |
| geom-gcn-geometric-graph-convolutional-1 | 57.58 |
| graphrare-reinforcement-learning-enhanced | 86.76±5.80 |
| graph-neural-reaction-diffusion-models | 93.51 ± 5.93 |
| revisiting-heterophily-for-graph-neural | 86.76 ± 4.75 |
| joint-adaptive-feature-smoothing-and-topology | 81.35 ± 5.32 |
| transitivity-preserving-graph-representation | 86.67 ±8.31 |
| unigap-a-universal-and-adaptive-graph | 86.52 ± 4.8 |