HyperAIHyperAI超神経

Command Palette

Search for a command to run...

プラットフォーム

Node Classification On Coauthor Cs

評価指標

Accuracy

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

Paper Title
NCGCN96.64 ± 0.29Clarify Confused Nodes via Separated Learning
NCSAGE96.48 ± 0.25Clarify Confused Nodes via Separated Learning
GraphSAGE96.38±0.11Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification
3ference95.99%Inferring from References with Differences for Semi-Supervised Node Classification on Graphs
GNNMoE(GCN-like P)95.81±0.26Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification
CoLinkDist95.80%Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
CoLinkDistMLP95.74%Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
GNNMoE(GAT-like P)95.72±0.23Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification
LinkDistMLP95.68%Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
GNNMoE(SAGE-like P)95.68±0.24Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification
LinkDist95.66%Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
HH-GraphSAGE95.13%Half-Hop: A graph upsampling approach for slowing down message passing
GraphSAGE95.11%Half-Hop: A graph upsampling approach for slowing down message passing
Exphormer94.93±0.46%Exphormer: Sparse Transformers for Graphs
GCN-LPA94.8 ± 0.4Unifying Graph Convolutional Neural Networks and Label Propagation
HH-GCN94.71%Half-Hop: A graph upsampling approach for slowing down message passing
GCN94.06%Half-Hop: A graph upsampling approach for slowing down message passing
GCN (PPR Diffusion)93.01%Diffusion Improves Graph Learning
DAGNN (Ours)92.8%Towards Deeper Graph Neural Networks
SIGN91.98 ± 0.50SIGN: Scalable Inception Graph Neural Networks
0 of 23 row(s) selected.