Node Classification On Actor
المقاييس
Accuracy
النتائج
نتائج أداء النماذج المختلفة على هذا المعيار القياسي
جدول المقارنة
| اسم النموذج | Accuracy |
|---|---|
| cat-a-causally-graph-attention-network-for | 38.5±1.2 |
| mamba-based-graph-convolutional-networks | 37.97±0.91 |
| gcnh-a-simple-method-for-representation | 36.89 ± 1.50 |
| revisiting-heterophily-for-graph-neural | 36.26 ± 1.34 |
| neural-sheaf-diffusion-a-topological | 37.80 ± 1.22 |
| non-local-graph-neural-networks | 37.9 ± 1.3 |
| beyond-low-frequency-information-in-graph | 34.82 ± 1.35 |
| self-attention-dual-embedding-for-graphs-with | 37.91 ± 0.97 |
| transfer-entropy-in-graph-convolutional | - |
| learn-from-heterophily-heterophilous | 37.21 ± 1.35 |
| make-heterophily-graphs-better-fit-gnn-a | 37.43 ± 0.78 |
| signgt-signed-attention-based-graph | 38.65±0.32 |
| joint-adaptive-feature-smoothing-and-topology | 35.16 ± 0.9 |
| graph-neural-reaction-diffusion-models | 38.69 ± 1.41 |
| revisiting-heterophily-for-graph-neural | 36.31 ± 1.2 |
| revisiting-heterophily-for-graph-neural | 37.09 ± 1.32 |
| sign-is-not-a-remedy-multiset-to-multiset | 36.72 ± 1.6 |
| neural-sheaf-diffusion-a-topological | 37.79 ± 1.01 |
| heterophilous-distribution-propagation-for | 37.26 ± 0.67 |
| clarify-confused-nodes-through-separated | 43.16 ± 1.32 |
| finding-global-homophily-in-graph-neural | 37.7 ± 1.40 |
| addressing-heterophily-in-node-classification | 34.56 ± 0.76 |
| beyond-homophily-with-graph-echo-state-1 | 34.5 ± 0.8 |
| understanding-over-squashing-and-bottlenecks-1 | 28.42 ± 0.75 |
| mixture-of-experts-meets-decoupled-message | 37.76±0.98 |
| non-local-graph-neural-networks | 31.6 ± 1.0 |
| refining-latent-homophilic-structures-over | 38.87±1.0 |
| restructuring-graph-for-higher-homophily-via | 36.2 ± 1.0 |
| non-local-graph-neural-networks | 29.5 ± 1.3 |
| generalizing-graph-neural-networks-beyond | 34.49 ± 1.63 |
| mixture-of-experts-meets-decoupled-message | 37.59±1.36 |
| revisiting-heterophily-for-graph-neural | 36.14 ± 1.44 |
| revisiting-heterophily-for-graph-neural | 37.31 ± 1.09 |
| cn-motifs-perceptive-graph-neural-networks | 36.25 ± 0.98 |
| unigap-a-universal-and-adaptive-graph | 37.69 ± 1.2 |
| neural-sheaf-diffusion-a-topological | 37.81 ± 1.15 |
| enhancing-intra-class-information-extraction | 39.91 ± 2.41 |
| bregman-graph-neural-network | 35.92 ± 0.84 |
| higher-order-graph-convolutional-network-with | 41.81±0.52 |
| improving-graph-neural-networks-with-simple | 35.75 ± 0.96 |
| geom-gcn-geometric-graph-convolutional-1 | 30.3 |
| revisiting-heterophily-for-graph-neural | 36.63 ± 0.84 |
| diffusion-jump-gnns-homophiliation-via | 36.93 ± 0.84 |
| mixture-of-experts-meets-decoupled-message | 37.97±1.01 |
| generalizing-graph-neural-networks-beyond | 34.31 ± 1.31 |
| large-scale-learning-on-non-homophilous | 36.10 ± 1.55 |
| clarify-confused-nodes-through-separated | 43.89 ± 1.33 |
| two-sides-of-the-same-coin-heterophily-and | 37.54 ± 1.56 |
| the-heterophilic-snowflake-hypothesis | 35.99 |
| ordered-gnn-ordering-message-passing-to-deal | 37.99 ± 1.00 |
| mixhop-higher-order-graph-convolution | 32.22 ± 2.34 |
| simple-truncated-svd-based-model-for-node | 34.59 ± 1.32 |
| revisiting-heterophily-for-graph-neural | 35.49 ± 1.06 |
| geom-gcn-geometric-graph-convolutional-1 | 31.63 |
| universal-deep-gnns-rethinking-residual | 36.13 ± 1.21 |
| revisiting-heterophily-for-graph-neural | 36.04 ± 0.83 |
| diffwire-inductive-graph-rewiring-via-the | 29.35 |
| simple-and-deep-graph-convolutional-networks-1 | 37.44 ± 1.30 |
| breaking-the-limit-of-graph-neural-networks | 36.53 ± 0.77 |
| diffwire-inductive-graph-rewiring-via-the | 31.98 |
| finding-global-homophily-in-graph-neural | 37.35 ± 1.30 |
| geom-gcn-geometric-graph-convolutional-1 | 29.09 |