Node Classification On Pubmed

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	91.64 ± 0.53	Clarify Confused Nodes via Separated Learning
NCSAGE	91.55 ± 0.38	Clarify Confused Nodes via Separated Learning
ACMII-Snowball-3	91.31 ± 0.6	Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?	-
ACM-GCN	90.74 ± 0.5	Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?	-
Graph-MLP + SAF	90.64 ± 0.46%	The Split Matters: Flat Minima Methods for Improving the Performance of GNNs
ACMII-Snowball-2	90.56 ± 0.39	Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?	-
NodeNet	90.21%	NodeNet: A Graph Regularised Neural Network for Node Classification	-
CNMPGNN	90.07± 0.43	CN-Motifs Perceptive Graph Neural Networks	-
CoLinkDist	89.58%	Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
CoLinkDistMLP	89.53%	Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
SSP	89.36 ± 0.57	Optimization of Graph Neural Networks with Natural Gradient Descent
3ference	88.90	Inferring from References with Differences for Semi-Supervised Node Classification on Graphs	-
SplineCNN	88.88%	SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels
LinkDist	88.86%	Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
LinkDistMLP	88.79%	Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
GCN + Mixup	87.9%	Mixup for Node and Graph Classification	-
GCN-LPA	87.8 ± 0.6	Unifying Graph Convolutional Neural Networks and Label Propagation
CGT	86.86±0.12	Mitigating Degree Biases in Message Passing Mechanism by Utilizing Community Structures
GRACE	86.7 ± 0.1	Deep Graph Contrastive Representation Learning
CT-Layer (PE)	86.07	DiffWire: Inductive Graph Rewiring via the Lovász Bound

0 of 69 row(s) selected.