HyperAI
StartseiteNeuigkeitenNeueste ForschungsarbeitenTutorialsDatensätzeWikiSOTALLM-ModelleGPU-RanglisteVeranstaltungen
Suche
Über
HyperAI

Node Classification On Coauthor Physics

Metriken

Accuracy

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname
Accuracy
Paper TitleRepository
GNNMoE(GCN-like P)97.03±0.13Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification
LinkDist96.87%Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
CoLinkDist97.05%Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
Exphormer96.89±0.09%Exphormer: Sparse Transformers for Graphs
GNNMoE(SAGE-like P)96.81±0.22Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification
DAGNN (Ours)94Towards Deeper Graph Neural Networks
GCN97.46 ± 0.10Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification
3ference97.22%Inferring from References with Differences for Semi-Supervised Node Classification on Graphs
GraphMix (GCN)94.49 ± 0.84GraphMix: Improved Training of GNNs for Semi-Supervised Learning
CoLinkDistMLP96.87%Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
LinkDistMLP96.91%Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
GNNMoE(GAT-like P)97.05±0.19Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification
NCSAGE98.69 ± 0.26Clarify Confused Nodes via Separated Learning
NCGCN98.63 ± 0.24Clarify Confused Nodes via Separated Learning
0 of 14 row(s) selected.