Node Classification On Coauthor Cs

评估指标

Accuracy

评测结果

各个模型在此基准测试上的表现结果

		Paper Title	Repository
NCGCN	96.64 ± 0.29	Clarify Confused Nodes via Separated Learning
NCSAGE	96.48 ± 0.25	Clarify Confused Nodes via Separated Learning
GraphSAGE	96.38±0.11	Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification
3ference	95.99%	Inferring from References with Differences for Semi-Supervised Node Classification on Graphs	-
GNNMoE(GCN-like P)	95.81±0.26	Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification
CoLinkDist	95.80%	Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
CoLinkDistMLP	95.74%	Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
GNNMoE(GAT-like P)	95.72±0.23	Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification
LinkDistMLP	95.68%	Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
GNNMoE(SAGE-like P)	95.68±0.24	Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification
LinkDist	95.66%	Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
HH-GraphSAGE	95.13%	Half-Hop: A graph upsampling approach for slowing down message passing
GraphSAGE	95.11%	Half-Hop: A graph upsampling approach for slowing down message passing
Exphormer	94.93±0.46%	Exphormer: Sparse Transformers for Graphs
GCN-LPA	94.8 ± 0.4	Unifying Graph Convolutional Neural Networks and Label Propagation
HH-GCN	94.71%	Half-Hop: A graph upsampling approach for slowing down message passing
GCN	94.06%	Half-Hop: A graph upsampling approach for slowing down message passing
GCN (PPR Diffusion)	93.01%	Diffusion Improves Graph Learning
DAGNN (Ours)	92.8%	Towards Deeper Graph Neural Networks
SIGN	91.98 ± 0.50	SIGN: Scalable Inception Graph Neural Networks

0 of 23 row(s) selected.