|
gptkbp:instanceOf
|
gptkb:convolutional_neural_network
|
|
gptkbp:application
|
computer vision
natural language processing
recommendation systems
social network analysis
knowledge graph completion
molecular property prediction
traffic prediction
|
|
gptkbp:field
|
gptkb:artificial_intelligence
gptkb:machine_learning
deep learning
|
|
gptkbp:hasConcept
|
message passing
node embedding
update function
aggregation function
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
GNN
|
|
gptkbp:input
|
graphs
edges
nodes
|
|
gptkbp:limitation
|
scalability
training instability
expressiveness
over-smoothing
|
|
gptkbp:notableConference
|
gptkb:ICLR
gptkb:ICML
gptkb:NeurIPS
|
|
gptkbp:notableContributor
|
gptkb:Yoshua_Bengio
gptkb:Petar_Veličković
gptkb:Jure_Leskovec
gptkb:Thomas_Kipf
|
|
gptkbp:notablePublication
|
Kipf & Welling, 2017
Scarselli et al., 2009
Velickovic et al., 2018
|
|
gptkbp:notableVariant
|
gptkb:Graph_Convolutional_Network
gptkb:Graph_Attention_Network
gptkb:Message_Passing_Neural_Network
|
|
gptkbp:platform
|
gptkb:TensorFlow_GNN
gptkb:PyTorch_Geometric
gptkb:Deep_Graph_Library
|
|
gptkbp:proposedBy
|
2005
|
|
gptkbp:relatedTo
|
gptkb:transformation
gptkb:convolutional_neural_network
recurrent neural network
|
|
gptkbp:standsFor
|
gptkb:convolutional_neural_network
|
|
gptkbp:trainer
|
self-supervised learning
supervised learning
semi-supervised learning
unsupervised learning
|
|
gptkbp:usedFor
|
graph classification
link prediction
node classification
graph-structured data
|
|
gptkbp:bfsParent
|
gptkb:Niger_National_Guard
|
|
gptkbp:bfsLayer
|
7
|