Expressiveness and Approximation Properties of Graph Neural Networks.
Floris GeertsJuan L. ReutterPublished in: CoRR (2022)
Keyphrases
- neural network
- pattern recognition
- random walk
- graph properties
- neural nets
- desirable properties
- genetic algorithm
- approximation error
- learning rules
- directed acyclic graph
- neural network model
- artificial neural networks
- bipartite graph
- graph theory
- graph structure
- error bounds
- multi layer
- graph databases
- back propagation
- radial basis function
- graph model
- undirected graph
- graph representation
- graph theoretic
- random graphs
- fuzzy logic
- structural properties