HyperAI
AccueilActualitésArticles de recherche récentsTutorielsEnsembles de donnéesWikiSOTAModèles LLMClassement GPUÉvénements
Recherche
À propos
HyperAI

Node Classification On Amazon Photo 1

Métriques

Accuracy

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle
Accuracy
Paper TitleRepository
CoLinkDist94.36%Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
GraphSAGE96.78 ± 0.23Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification
CoLinkDistMLP94.12%Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
GNNMoE(GAT-like P)95.71±0.37Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification
GCN96.10 ± 0.46Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification
GAT96.60 ± 0.33Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification
3ference95.05%Inferring from References with Differences for Semi-Supervised Node Classification on Graphs
LinkDist93.75%Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
GNNMoE(GCN-like P)95.81±0.41Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification
GNNMoE(SAGE-like P)95.46±0.24Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification
LinkDistMLP93.83%Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
0 of 11 row(s) selected.