Quantifying the reproducibility of graph neural networks using multigraph data representation.
Ahmed NebliMohammed Amine GharsallaouiZeynep GürlerIslem RekikAlzheimer's Disease Neuroimaging InitiativePublished in: Neural Networks (2022)
Keyphrases
- data representation
- neural network
- pattern recognition
- graph structure
- graph kernels
- dimensionality reduction
- graph theory
- artificial neural networks
- back propagation
- directed graph
- representational power
- data representations
- subspace learning
- structured data
- random walk
- weighted graph
- databases
- graph mining
- principal component analysis
- similarity measure
- feature construction
- database systems
- image processing
- tensor decomposition