Node Classification On Chameleon
المقاييس
Accuracy
النتائج
نتائج أداء النماذج المختلفة على هذا المعيار القياسي
جدول المقارنة
| اسم النموذج | Accuracy |
|---|---|
| gcnh-a-simple-method-for-representation | 71.56±1.86 |
| edge-directionality-improves-learning-on | 79.71±1.26 |
| generalizing-graph-neural-networks-beyond | 52.96 ± 2.09 |
| simple-and-deep-graph-convolutional-networks-1 | 63.86 ± 3.04 |
| generalizing-graph-neural-networks-beyond | 58.38 ± 1.76 |
| revisiting-heterophily-for-graph-neural | 69.14 ± 1.91 |
| self-attention-dual-embedding-for-graphs-with | 75.57±1.57 |
| non-local-graph-neural-networks | 50.7 ± 2.2 |
| revisiting-heterophily-for-graph-neural | 63.99 ± 1.66 |
| cn-motifs-perceptive-graph-neural-networks | 73.29±1.29 |
| cat-a-causally-graph-attention-network-for | 69.9±1.0 |
| large-scale-learning-on-non-homophilous | 68.42 ± 1.38 |
| understanding-over-squashing-and-bottlenecks-1 | 42.73±0.15 |
| refining-latent-homophilic-structures-over | 72.31±1.6 |
| non-local-graph-neural-networks | 70.1 ± 2.9 |
| restructuring-graph-for-higher-homophily-via | 68.4 ± 2.3 |
| improving-graph-neural-networks-with-simple | 78.14±1.25 |
| sheaf-neural-networks-with-connection | 65.21±2.04 |
| enhancing-intra-class-information-extraction | 72.13±2.11 |
| sign-is-not-a-remedy-multiset-to-multiset | 75.20 ± 2.3 |
| geom-gcn-geometric-graph-convolutional-1 | 60.9 |
| beyond-homophily-with-graph-echo-state-1 | 76.2±1.2 |
| geom-gcn-geometric-graph-convolutional-1 | 59.96 |
| mixhop-higher-order-graph-convolution | 60.50 ± 2.53 |
| beyond-low-frequency-information-in-graph | 46.07 ± 2.11 |
| finding-global-homophily-in-graph-neural | 69.78±2.42 |
| neural-sheaf-diffusion-a-topological | 68.04 ± 1.58 |
| breaking-the-limit-of-graph-neural-networks | 65.24 ± 0.87 |
| revisiting-heterophily-for-graph-neural | 74.56 ± 2.08 |
| higher-order-graph-convolutional-network-with | 68.47±0.45 |
| revisiting-heterophily-for-graph-neural | 74.47 ± 1.84 |
| fdgatii-fast-dynamic-graph-attention-with | 65.1754 |
| the-heterophilic-snowflake-hypothesis | 70.18 |
| graphrare-reinforcement-learning-enhanced | 69.28±1.90 |
| two-sides-of-the-same-coin-heterophily-and | 71.14 ± 1.84 |
| universal-deep-gnns-rethinking-residual | 74.53±1.19 |
| geom-gcn-geometric-graph-convolutional-1 | 60.31 |
| signgt-signed-attention-based-graph | 74.31±1.24 |
| make-heterophily-graphs-better-fit-gnn-a | 74.57±2.56 |
| heterophilic-graph-neural-networks | 59.14±2.42 |
| improving-graph-neural-networks-by-learning | 79.69±1.35 |
| transfer-entropy-in-graph-convolutional | 71.14 ± 1.84 |
| revisiting-heterophily-for-graph-neural | 74.76 ± 2.2 |
| improving-graph-neural-networks-with-simple | 78.27±1.28 |
| learn-from-heterophily-heterophilous | 68.86 ± 1.45 |
| simple-truncated-svd-based-model-for-node | 77.48±0.80 |
| label-wise-message-passing-graph-neural | 74.4±1.4 |
| holonets-spectral-convolutions-do-extend-to | 80.33±1.19 |
| revisiting-heterophily-for-graph-neural | 59.21 ± 2.22 |
| finding-global-homophily-in-graph-neural | 71.21±1.84 |
| ordered-gnn-ordering-message-passing-to-deal | 72.28±2.29 |
| diffusion-jump-gnns-homophiliation-via | 80.48±1.46 |
| revisiting-heterophily-for-graph-neural | 74.41 ± 1.49 |
| neural-sheaf-diffusion-a-topological | 67.93 ± 1.58 |
| non-local-graph-neural-networks | 65.7 ± 1.4 |
| neural-sheaf-diffusion-a-topological | 68.68 ± 1.73 |
| revisiting-heterophily-for-graph-neural | 68.46 ± 1.7 |
| transitivity-preserving-graph-representation | 69.78 ±3.21 |
| joint-adaptive-feature-smoothing-and-topology | 62.59 ± 2.04 |
| breaking-the-entanglement-of-homophily-and | 46.2±1.3 |
| graph-neural-reaction-diffusion-models | 74.79 ± 2.14 |