Link Prediction
Link prediction is a task in graph and network analysis aimed at predicting missing or future connections between nodes in a network. Based on partially observed network structures and known connections, the goal of link prediction is to infer the links that are most likely to be added or overlooked, thereby uncovering potential relationships and enhancing the integrity of the network. This task holds significant application value in areas such as network science, social network analysis, and recommendation systems.
ResAttArg
KG2Vec LSTM
GATNE-I
GATNE-T
ComplEx-N3-RP
Walkpooling
GraphStar (double weight on positive examples)
ComplEx-N3-RP
ULTRA
GatedGCN-PE
NESS
GraphStar (double weight on positive examples)
GLACE
ConE
Decagon
HSRL (DW)
HOGCN
BoxE
Prob-CBR
AutoKGE
MEI (small)
ComplEx-N3-RP
kNN-KGE
ParTransH
SPA
ConE
TNTComplEx (x10)
TNTComplEx (x10)
Event2vec
MEI (small)
PyTorch BigGraph
PEAGAT
Prob-CBR
Edge2Node
RESCAL
ViT-PS
HGCN
Walkpooling
GraphStar (double weight on positive examples)
GLACE
EGT
LP-BERT
SEAL
HAHE
BANE
Asymmetric Transitivity Preservation
TimePlex
HAHE
GraphVite (zhu2019graphvite)
ParTransH
GFA-NN
Hyper-SAGNN-W
TNTComplEx (x10)
MEIM
SEEK
TransC (bern)
PEAGAT
PyTorch BigGraph