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

		Paper Title
OGC	77.5	From Cluster Assumption to Graph Convolution: Graph-based Semi-Supervised Learning Revisited
GRAND	75.4 ± 0.4	Graph Random Neural Network for Semi-Supervised Learning on Graphs
LDS-GNN	75.0%	Learning Discrete Structures for Graph Neural Networks
Graph-MLP + PGN	74.73 ± 0.6%	The Split Matters: Flat Minima Methods for Improving the Performance of GNNs
CPF-tra-APPNP	74.6%	Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Framework
GraphMix(GCN)	74.52 ± 0.59	GraphMix: Improved Training of GNNs for Semi-Supervised Learning
G3NN	74.5%	A Flexible Generative Framework for Graph-based Semi-supervised Learning
SSP	74.28 ± 0.67%	Optimization of Graph Neural Networks with Natural Gradient Descent
GEM	74.2	Graph Entropy Minimization for Semi-supervised Node Classification
GGCM	74.2	From Cluster Assumption to Graph Convolution: Graph-based Semi-Supervised Learning Revisited
Truncated Krylov	73.86%	Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks
SSGC	73.6	Simple Spectral Graph Convolution
OKDEEM	73.53	Graph Entropy Minimization for Semi-supervised Node Classification
SEGCN	73.4 ± 0.7	Every Node Counts: Self-Ensembling Graph Convolutional Networks for Semi-Supervised Learning
GCNII	73.4%	Simple and Deep Graph Convolutional Networks
Snowball (tanh)	73.32%	Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks
DSGCN	73.3	Bridging the Gap Between Spectral and Spatial Domains in Graph Neural Networks
GCN+GAugO	73.3 ± 1.1	Data Augmentation for Graph Neural Networks
DAGNN (Ours)	73.3 ± 0.6	Towards Deeper Graph Neural Networks
GCN	73.14± 0.67	Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification

0 of 40 row(s) selected.

Command Palette

Node Classification On Citeseer With Public

評価指標

評価結果