Node Classification On Pubmed

Metrics

Accuracy

Results

Performance results of various models on this benchmark

Model Name	Accuracy	Paper Title	Repository
DANMF	63.93%	Deep Autoencoder-like Nonnegative Matrix Factorization for Community Detection
Cleora	80.2	Cleora: A Simple, Strong and Scalable Graph Embedding Scheme
GCN + AdaGraph (AG)	77.4 ± 0.2	Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View	-
SDRF	79.10±0.11	Understanding over-squashing and bottlenecks on graphs via curvature
MMA	86.00%	Multi-Mask Aggregators for Graph Neural Networks
3ference	88.90	Inferring from References with Differences for Semi-Supervised Node Classification on Graphs
NCSAGE	91.55 ± 0.38	Clarify Confused Nodes via Separated Learning
APPNP	79.73 ± 0.31	Predict then Propagate: Graph Neural Networks meet Personalized PageRank
GResNet(GCN)	81.7%	GResNet: Graph Residual Network for Reviving Deep GNNs from Suspended Animation
GResNet(GAT)	82.2%	GResNet: Graph Residual Network for Reviving Deep GNNs from Suspended Animation
LinkDist	88.86%	Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
GCN-LPA	87.8 ± 0.6	Unifying Graph Convolutional Neural Networks and Label Propagation
AGNN-w/o share	79.7 ± 0.4%	Auto-GNN: Neural Architecture Search of Graph Neural Networks	-
APPNP	79.4 ± 2.2	Fast Graph Representation Learning with PyTorch Geometric
ChebNet	74.4%	Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
Planetoid*	77.2%	Revisiting Semi-Supervised Learning with Graph Embeddings
NCGCN	91.64 ± 0.53	Clarify Confused Nodes via Separated Learning
Graph-Bert	79.3%	Graph-Bert: Only Attention is Needed for Learning Graph Representations
N-GCN	79.5%	N-GCN: Multi-scale Graph Convolution for Semi-supervised Node Classification
ACM-GCN	90.74 ± 0.5	Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?	-

0 of 69 row(s) selected.