Node Classification On Pubmed With Public

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
OGC	83.4%	From Cluster Assumption to Graph Convolution: Graph-based Semi-Supervised Learning Revisited
CPF-tra-GCNII	83.20%	Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Framework
GRAND	82.7 ± 0.6	Graph Random Neural Network for Semi-Supervised Learning on Graphs
Graph-MLP + ASAM	82.60 ± 0.80%	The Split Matters: Flat Minima Methods for Improving the Performance of GNNs
DSGCN	81.9%	Bridging the Gap Between Spectral and Spatial Domains in Graph Neural Networks
SuperGAT MX	81.7%	How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision
Truncated Krylov	81.7%	Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks
GCN	81.12 ± 0.52	Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification
GraphMix (GCN)	80.98 ± 0.55	GraphMix: Improved Training of GNNs for Semi-Supervised Learning
G-APPNP	80.95%	Pre-train and Learn: Preserve Global Information for Graph Neural Networks
GGCM	80.8%	From Cluster Assumption to Graph Convolution: Graph-based Semi-Supervised Learning Revisited
DAGNN (Ours)	80.5 ± 0.5	Towards Deeper Graph Neural Networks
GCN(predicted-targets)	80.42%	GraphMix: Improved Training of GNNs for Semi-Supervised Learning
SSGC	80.4	Simple Spectral Graph Convolution	-
GCNII	80.2%	Simple and Deep Graph Convolutional Networks
SSP	80.06 ± 0.34%	Optimization of Graph Neural Networks with Natural Gradient Descent
AIR-GCN	80%	GraphAIR: Graph Representation Learning with Neighborhood Aggregation and Interaction
Graph-MLP	79.91	Graph Entropy Minimization for Semi-supervised Node Classification
H-GCN	79.8%	Hierarchical Graph Convolutional Networks for Semi-supervised Node Classification
GCN+DropEdge	79.60%	-	-

0 of 37 row(s) selected.