Node Classification On Coauthor Cs
المقاييس
Accuracy
النتائج
نتائج أداء النماذج المختلفة على هذا المعيار القياسي
جدول المقارنة
| اسم النموذج | Accuracy |
|---|---|
| half-hop-a-graph-upsampling-approach-for | 94.71% |
| distilling-self-knowledge-from-contrastive | 95.68% |
| distilling-self-knowledge-from-contrastive | 95.66% |
| clarify-confused-nodes-through-separated | 96.48 ± 0.25 |
| distilling-self-knowledge-from-contrastive | 95.80% |
| exphormer-sparse-transformers-for-graphs | 94.93±0.46% |
| unifying-graph-convolutional-neural-networks-1 | 94.8 ± 0.4 |
| snore-scalable-unsupervised-learning-of | 88.7% |
| inferring-from-references-with-differences | 95.99% |
| sign-scalable-inception-graph-neural-networks | 91.98 ± 0.50 |
| distilling-self-knowledge-from-contrastive | 95.74% |
| graph-infoclust-leveraging-cluster-level-node | 89.4 ± 0.4 |
| mixture-of-experts-meets-decoupled-message | 95.68±0.24 |
| towards-deeper-graph-neural-networks | 92.8% |
| clarify-confused-nodes-through-separated | 96.64 ± 0.29 |
| half-hop-a-graph-upsampling-approach-for | 94.06% |
| diffusion-improves-graph-learning-1 | 93.01% |
| half-hop-a-graph-upsampling-approach-for | 95.11% |
| mixture-of-experts-meets-decoupled-message | 95.72±0.23 |
| graphmix-regularized-training-of-graph-neural | 91.83 ± 0.51 |
| half-hop-a-graph-upsampling-approach-for | 95.13% |
| classic-gnns-are-strong-baselines-reassessing | 96.38±0.11 |
| mixture-of-experts-meets-decoupled-message | 95.81±0.26 |