Node Classification On Pubmed With Public
المقاييس
Accuracy
النتائج
نتائج أداء النماذج المختلفة على هذا المعيار القياسي
جدول المقارنة
| اسم النموذج | Accuracy |
|---|---|
| towards-deeper-graph-neural-networks | 80.5 ± 0.5 |
| gated-graph-sequence-neural-networks | 75.8% |
| convolutional-neural-networks-on-graphs-with | 69.8% |
| how-to-find-your-friendly-neighborhood-graph-1 | 81.7% |
| distilling-self-knowledge-from-contrastive | 72.41% |
| pre-train-and-learn-preserve-global | 80.95% |
| break-the-ceiling-stronger-multi-scale-deep | 81.7% |
| inductive-representation-learning-on-large | 76.8% |
| optimization-of-graph-neural-networks-with | 80.06 ± 0.34% |
| classic-gnns-are-strong-baselines-reassessing | 81.12 ± 0.52 |
| graphair-graph-representation-learning-with | 80% |
| from-cluster-assumption-to-graph-convolution | 83.4% |
| lanczosnet-multi-scale-deep-graph | 78.3 ± 0.3 |
| graphmix-regularized-training-of-graph-neural | 80.42% |
| break-the-ceiling-stronger-multi-scale-deep | 79.10% |
| from-cluster-assumption-to-graph-convolution | 80.8% |
| simple-spectral-graph-convolution | 80.4 |
| graph-entropy-minimization-for-semi | 79.91 |
| النموذج 19 | 79.60% |
| distilling-self-knowledge-from-contrastive | 75.41% |
| graph-random-neural-network | 82.7 ± 0.6 |
| distilling-self-knowledge-from-contrastive | 74.06% |
| distilling-self-knowledge-from-contrastive | 75.64% |
| graph-entropy-minimization-for-semi | 78.48 |
| simple-and-deep-graph-convolutional-networks-1 | 80.2% |
| the-split-matters-flat-minima-methods-for | 82.60 ± 0.80% |
| bridging-the-gap-between-spectral-and-spatial | 81.9% |
| semi-supervised-node-classification-via | 79.8% |
| graph-attention-networks | 79.0% |
| extract-the-knowledge-of-graph-neural | 83.20% |
| lanczosnet-multi-scale-deep-graph | 78.1 ± 0.4 |
| diffusion-convolutional-neural-networks | 76.8% |
| every-node-counts-self-ensembling-graph | 78.9 ± 0.7 |
| break-the-ceiling-stronger-multi-scale-deep | 79.16% |
| graphmix-regularized-training-of-graph-neural | 80.98 ± 0.55 |
| convolutional-networks-on-graphs-for-learning | 76.0% |
| a-flexible-generative-framework-for-graph | 78.4% |