Statements (59)
| Predicate | Object |
|---|---|
| gptkbp:instance_of |
gptkb:neural_networks
|
| gptkbp:based_on |
gptkb:Chebyshev_polynomials
|
| gptkbp:developed_by |
Michele Defferrard
Xavier Bresson |
| gptkbp:has_achieved |
state-of-the-art results
|
| gptkbp:has_applications_in |
recommendation systems
social network analysis biological networks |
| gptkbp:has_limitations |
sensitivity to noise
requires graph structure |
| https://www.w3.org/2000/01/rdf-schema#label |
Cheb Net
|
| gptkbp:improves |
spectral graph convolution
|
| gptkbp:is_adopted_by |
research institutions
startups industry applications tech companies |
| gptkbp:is_applied_in |
semi-supervised learning
graph classification |
| gptkbp:is_challenged_by |
scalability issues
new architectures advancements in GNNs |
| gptkbp:is_compared_to |
gptkb:GCN
GAT |
| gptkbp:is_evaluated_by |
Citeseer dataset
Cora dataset Pubmed dataset |
| gptkbp:is_explored_in |
theses
numerous studies conference papers journal articles |
| gptkbp:is_implemented_in |
gptkb:Tensor_Flow
gptkb:Py_Torch |
| gptkbp:is_influenced_by |
signal processing
graph theory numerical analysis machine learning theory |
| gptkbp:is_notable_for |
scalability
efficient computation theoretical foundation flexibility in architecture robustness to overfitting |
| gptkbp:is_part_of |
gptkb:machine_learning
deep learning |
| gptkbp:is_related_to |
convolutional neural networks
spectral methods |
| gptkbp:is_supported_by |
gptkb:Publications
gptkb:scientific_community open-source implementations |
| gptkbp:is_used_in |
link prediction
node classification graph generation graph-based learning tasks |
| gptkbp:published_in |
gptkb:2016
|
| gptkbp:requires |
graph Laplacian
|
| gptkbp:suitable_for |
large graphs
|
| gptkbp:uses |
localized filters
|
| gptkbp:utilizes |
K-order Chebyshev polynomials
|
| gptkbp:bfsParent |
gptkb:neural_networks
|
| gptkbp:bfsLayer |
4
|