Node Classification
Node Classification is a machine learning task in graph data analysis, aiming to predict unknown attributes of nodes in a graph based on the attributes of the nodes and their relationships. This task is implemented through models such as Graph Neural Networks, and its performance is typically evaluated using metrics like Accuracy and F1 on benchmark datasets such as Cora, Citeseer, and Pubmed. Node Classification has significant application value in areas like social network analysis, recommendation systems, and bioinformatics.
GraRep
R-GCN
BoP
GAT
GTAN
GraphSAGE
Cluster-GCN
R-GCN
HH-GCN
CPF-ind-GAT
Exphormer
FaberNet
ASDNet [ASDNet_ICCV2021]
PathNet
SCENE
GraphMix (GCN)
GraphMix (GCN)
DAOR
ISNE
plantcelltype-EdgeDeeperGCN
DJ-GNN
GREAD-BS
TransGNN
MT-GCN
VCHN
Geom-GCN
IncepGCN+DropEdge
GraphMix (GCN)
GraphMix (GCN)
GRIT
CoLinkDist
GCN-LPA
CoLinkDist
NeuralWalker
SSP
CPF-ind_APPNP
VHCN
Truncated Krylov
NLGAT
CPF-tra-GCNII
Self-supervised GraphMAE
CPF-tra-APPNP
CoLinkDist
GCNII
CoLinkDist
GraphMix (GCN)
OGC
HH-GraphSAGE
LW-GCN
GRACE
RR-GCN-PPV
RR-GCN-PPV
GCN_cheby (Kipf and Welling, 2017)
GNNMoE(GCN-like P)
GCN+GAugM (Zhao et al., 2021)
GESN
FastGCN
APPNP
LaBSE
RR-GCN-PPV
DFNet-ATT
SAN+LapPE
CKGCN
EGT
GloGNN++
GraphSAGE
NeuralWalker
g2-MLP
ClusterGCN
Truncated Krylov
Truncated Krylov
GCNII
GraphSAGE+DropEdge
GraphMix (GCN)
OGC
GCN
BNS-GCN
NCSAGE
ScaleNet
2-HiGCN
ACM-GCN++
Polynormer
Dual-Net GNN
DEMO-Net(weight)
DAOR
A2DUG
CGT
DEMO-Net(weight)
GraphGAN
5-HiGCN
ACM-GCN++
LINE