Node Classification On Amz Photo

المقاييس

Accuracy

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

		Paper Title
NCSAGE	95.93 ± 0.36	Clarify Confused Nodes via Separated Learning
CGT	95.73±0.84	Mitigating Degree Biases in Message Passing Mechanism by Utilizing Community Structures
NCGCN	95.45 ± 0.45	Clarify Confused Nodes via Separated Learning
Exphormer	95.35±0.22%	Exphormer: Sparse Transformers for Graphs
GraphSAGE	95.03%	Half-Hop: A graph upsampling approach for slowing down message passing
HH-GraphSAGE	94.55%	Half-Hop: A graph upsampling approach for slowing down message passing
HH-GCN	94.52%	Half-Hop: A graph upsampling approach for slowing down message passing
CPF-ind-GAT	94.10%	Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Framework
GCN	93.59%	Half-Hop: A graph upsampling approach for slowing down message passing
JK (Heat Diffusion)	92.93%	Diffusion Improves Graph Learning
GLNN	92.11± 1.08%	Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation
DAGNN (Ours)	92%	Towards Deeper Graph Neural Networks
SIGN	91.72 ± 1.20	SIGN: Scalable Inception Graph Neural Networks
Graph InfoClust (GIC)	90.4 ± 1.0	Graph InfoClust: Leveraging cluster-level node information for unsupervised graph representation learning

0 of 14 row(s) selected.

Node Classification On Amz Photo | SOTA | HyperAI