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

模型名称	Accuracy	Paper Title	Repository
HH-GCN	94.71%	Half-Hop: A graph upsampling approach for slowing down message passing
LinkDistMLP	95.68%	Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
LinkDist	95.66%	Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
NCSAGE	96.48 ± 0.25	Clarify Confused Nodes via Separated Learning
CoLinkDist	95.80%	Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
Exphormer	94.93±0.46%	Exphormer: Sparse Transformers for Graphs
GCN-LPA	94.8 ± 0.4	Unifying Graph Convolutional Neural Networks and Label Propagation
SNoRe	88.7%	SNoRe: Scalable Unsupervised Learning of Symbolic Node Representations	-
3ference	95.99%	Inferring from References with Differences for Semi-Supervised Node Classification on Graphs
SIGN	91.98 ± 0.50	SIGN: Scalable Inception Graph Neural Networks
CoLinkDistMLP	95.74%	Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
Graph InfoClust (GIC)	89.4 ± 0.4	Graph InfoClust: Leveraging cluster-level node information for unsupervised graph representation learning
GNNMoE(SAGE-like P)	95.68±0.24	Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification
DAGNN (Ours)	92.8%	Towards Deeper Graph Neural Networks
NCGCN	96.64 ± 0.29	Clarify Confused Nodes via Separated Learning
GCN	94.06%	Half-Hop: A graph upsampling approach for slowing down message passing
GCN (PPR Diffusion)	93.01%	Diffusion Improves Graph Learning
GraphSAGE	95.11%	Half-Hop: A graph upsampling approach for slowing down message passing
GNNMoE(GAT-like P)	95.72±0.23	Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification
GraphMix (GCN)	91.83 ± 0.51	GraphMix: Improved Training of GNNs for Semi-Supervised Learning

0 of 23 row(s) selected.