Accueil Actualités Articles de recherche récents Tutoriels Ensembles de données Wiki SOTA Modèles LLM Classement GPU Événements

Français

Node Classification On Amazon Computers 1

Métriques

Accuracy

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	Accuracy	Paper Title	Repository
3ference	90.74%	Inferring from References with Differences for Semi-Supervised Node Classification on Graphs
GraphSAGE	93.25±0.14	Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification
CGT	91.45±0.58	Mitigating Degree Biases in Message Passing Mechanism by Utilizing Community Structures
GCN	93.99±0.12	Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification
GNNMoE(GCN-like P)	92.17±0.50	Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification
CoLinkDistMLP	88.85%	Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
GAT	94.09±0.37	Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification
GNNMoE(SAGE-like P)	91.85±0.39	Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification
CoLinkDist	89.42%	Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
GNNMoE(GAT-like P)	91.98±0.46	Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification
LinkDist	89.49%	Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
LinkDistMLP	89.44%	Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages

0 of 12 row(s) selected.