Node Classification On Citeseer With Public

評価指標

Accuracy

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名	Accuracy	Paper Title	Repository
AIR-GCN	72.9%	GraphAIR: Graph Representation Learning with Neighborhood Aggregation and Interaction
LanczosNet	66.2 ± 1.9	LanczosNet: Multi-Scale Deep Graph Convolutional Networks
DSGCN	73.3	Bridging the Gap Between Spectral and Spatial Domains in Graph Neural Networks
LinkDist	70.27%	Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
GRAND	75.4 ± 0.4	Graph Random Neural Network for Semi-Supervised Learning on Graphs
Snowball (tanh)	73.32%	Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks
G-APPNP	72%	Pre-train and Learn: Preserve Global Information for Graph Neural Networks
IncepGCN+DropEdge	72.70%	-	-
CPF-tra-APPNP	74.6%	Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Framework
CoLinkDist	70.79%	Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
SSP	74.28 ± 0.67%	Optimization of Graph Neural Networks with Natural Gradient Descent
LDS-GNN	75.0%	Learning Discrete Structures for Graph Neural Networks
OGC	77.5	From Cluster Assumption to Graph Convolution: Graph-based Semi-Supervised Learning Revisited
CoLinkDistMLP	70.96%	Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
SEGCN	73.4 ± 0.7	Every Node Counts: Self-Ensembling Graph Convolutional Networks for Semi-Supervised Learning
GAT	72.5 ± 0.7%	Graph Attention Networks
SuperGAT MX	72.6%	How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision	-
GraphMix(GCN)	74.52 ± 0.59	GraphMix: Improved Training of GNNs for Semi-Supervised Learning
GraphSAGE	67.2	Inductive Representation Learning on Large Graphs
SSGC	73.6	Simple Spectral Graph Convolution

0 of 40 row(s) selected.