HyperAI
الرئيسيةالأخبارأحدث الأوراق البحثيةالدروسمجموعات البياناتالموسوعةSOTAنماذج LLMلوحة الأداء GPUالفعاليات
البحث
حول
HyperAI

Node Classification On Amz Photo

المقاييس

Accuracy

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

اسم النموذج
Accuracy
Paper TitleRepository
GLNN92.11± 1.08%Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation
GraphSAGE95.03%Half-Hop: A graph upsampling approach for slowing down message passing
HH-GraphSAGE94.55%Half-Hop: A graph upsampling approach for slowing down message passing
NCSAGE95.93 ± 0.36Clarify Confused Nodes via Separated Learning
HH-GCN94.52%Half-Hop: A graph upsampling approach for slowing down message passing
CGT95.73±0.84Mitigating Degree Biases in Message Passing Mechanism by Utilizing Community Structures
Graph InfoClust (GIC)90.4 ± 1.0Graph InfoClust: Leveraging cluster-level node information for unsupervised graph representation learning
JK (Heat Diffusion)92.93%Diffusion Improves Graph Learning
Exphormer95.35±0.22%Exphormer: Sparse Transformers for Graphs
SIGN91.72 ± 1.20SIGN: Scalable Inception Graph Neural Networks
NCGCN95.45 ± 0.45Clarify Confused Nodes via Separated Learning
DAGNN (Ours)92%Towards Deeper Graph Neural Networks
GCN93.59%Half-Hop: A graph upsampling approach for slowing down message passing
CPF-ind-GAT94.10%Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Framework
0 of 14 row(s) selected.