Statements (55)
| Predicate | Object |
|---|---|
| gptkbp:instance_of |
gptkb:neural_networks
|
| gptkbp:applies_to |
graph-structured data
|
| gptkbp:can_be_combined_with |
recurrent neural networks
attention mechanisms |
| gptkbp:can_handle |
large-scale graphs
|
| gptkbp:developed_by |
gptkb:Thomas_Kipf
|
| gptkbp:has_applications_in |
computer vision
natural language processing |
| gptkbp:has_expansion |
gptkb:neural_networks
|
| gptkbp:has_limitations |
scalability issues
over-smoothing |
| https://www.w3.org/2000/01/rdf-schema#label |
GCN
|
| gptkbp:improves |
node classification
|
| gptkbp:is_adopted_by |
data scientists
AI researchers machine learning engineers |
| gptkbp:is_applied_in |
recommendation systems
social network analysis biological network analysis |
| gptkbp:is_based_on |
spectral graph theory
|
| gptkbp:is_compared_to |
other graph neural networks
traditional machine learning methods |
| gptkbp:is_considered_as |
state-of-the-art method
|
| gptkbp:is_evaluated_by |
Citeseer dataset
Cora dataset Pubmed dataset semi-supervised settings supervised settings unsupervised settings |
| gptkbp:is_implemented_in |
gptkb:Tensor_Flow
gptkb:Py_Torch |
| gptkbp:is_influenced_by |
gptkb:Cheb_Net
gptkb:Graph_SAGE GAT |
| gptkbp:is_known_for |
efficiency
flexibility scalability |
| gptkbp:is_part_of |
graph neural networks
|
| gptkbp:is_popular_in |
gptkb:academic_research
industry applications |
| gptkbp:is_related_to |
gptkb:machine_learning
deep learning |
| gptkbp:is_supported_by |
research papers
tutorials numerous libraries |
| gptkbp:is_used_in |
community detection
link prediction graph classification |
| gptkbp:performance |
graph-based tasks
|
| gptkbp:requires |
feature engineering
|
| gptkbp:used_for |
semi-supervised learning
|
| gptkbp:utilizes |
convolutional layers
|
| gptkbp:year_created |
gptkb:2016
|
| gptkbp:bfsParent |
gptkb:neural_networks
|
| gptkbp:bfsLayer |
4
|