HyperAI超神经
首页资讯最新论文教程数据集百科SOTALLM 模型天梯GPU 天梯顶会
全站搜索
关于
HyperAI超神经

Node Classification On Amazon Computers 1

评估指标

Accuracy

评测结果

各个模型在此基准测试上的表现结果

模型名称
Accuracy
Paper TitleRepository
3ference90.74%Inferring from References with Differences for Semi-Supervised Node Classification on Graphs
GraphSAGE93.25±0.14Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification
CGT91.45±0.58Mitigating Degree Biases in Message Passing Mechanism by Utilizing Community Structures
GCN93.99±0.12Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification
GNNMoE(GCN-like P)92.17±0.50Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification
CoLinkDistMLP88.85%Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
GAT94.09±0.37Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification
GNNMoE(SAGE-like P)91.85±0.39Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification
CoLinkDist89.42%Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
GNNMoE(GAT-like P)91.98±0.46Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification
LinkDist89.49%Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
LinkDistMLP89.44%Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
0 of 12 row(s) selected.