Node Classification On Cora

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

模型名称	Accuracy	Paper Title	Repository
GWNN	81.6%	Graph Wavelet Neural Network
GraphScattering	81.9%	Graph Convolutional Neural Networks via Scattering
GResNet(GAT)	85.5%	GResNet: Graph Residual Network for Reviving Deep GNNs from Suspended Animation
SF-GCN	83.3%	Structure fusion based on graph convolutional networks for semi-supervised classification	-
SNoRe	82.2%	SNoRe: Scalable Unsupervised Learning of Symbolic Node Representations	-
ACMII-GCN	88.95% ± 1.04%	Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?	-
TDGNN	85.35% ± 0.49%	Tree Decomposed Graph Neural Network
CT-Layer (PE)	83.66%	DiffWire: Inductive Graph Rewiring via the Lovász Bound
SEGCN	83.5% ± 0.4%	Every Node Counts: Self-Ensembling Graph Convolutional Networks for Semi-Supervised Learning
Planetoid*	75.7%	Revisiting Semi-Supervised Learning with Graph Embeddings
SDRF	82.76±0.23%	Understanding over-squashing and bottlenecks on graphs via curvature
LoopyNet	82.6%	GResNet: Graph Residual Network for Reviving Deep GNNs from Suspended Animation
CNMPGNN	88.20±1.22%	CN-Motifs Perceptive Graph Neural Networks	-
APPNP	82.2% ± 1.5%	Fast Graph Representation Learning with PyTorch Geometric
3ference	87.78%	Inferring from References with Differences for Semi-Supervised Node Classification on Graphs
GLNN	80.54± 1.35%	Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation
UGT	88.74±0.6%	Transitivity-Preserving Graph Representation Learning for Bridging Local Connectivity and Role-based Similarity
ChebNet	81.2%	Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
DGI	82.3 ± 0.6%	Deep Graph Infomax
DifNet	85.1%	Get Rid of Suspended Animation Problem: Deep Diffusive Neural Network on Graph Semi-Supervised Classification

0 of 72 row(s) selected.