Training Graph Neural Networks on Growing Stochastic Graphs.
Juan CerviñoLuana RuizAlejandro RibeiroPublished in: CoRR (2022)
Keyphrases
- neural network
- graph representation
- training process
- weighted graph
- graph theory
- graph structure
- graph matching
- graph databases
- directed graph
- graph construction
- graph theoretic
- graph clustering
- training algorithm
- graph classification
- graph mining
- labeled graphs
- graph properties
- graph model
- structural pattern recognition
- pattern recognition
- graph data
- graph theoretical
- graph search
- graph partitioning
- subgraph isomorphism
- bipartite graph
- adjacency matrix
- graph structures
- feedforward neural networks
- graph kernels
- graph isomorphism
- random graphs
- graph representations
- graph transformation
- reachability queries
- spanning tree
- undirected graph
- multi layer perceptron
- dynamic graph
- evolving graphs
- series parallel
- dense subgraphs
- graph patterns
- maximum clique
- graph embedding
- feed forward neural networks
- inexact graph matching
- topological information
- multilayer perceptron
- maximal cliques
- maximum common subgraph
- connected graphs
- training set
- connected dominating set
- maximum cardinality
- directed acyclic
- semi supervised
- graph layout
- random walk
- back propagation
- spectral decomposition
- structured data
- pattern mining
- real world graphs
- adjacency graph
- activation function
- web graph
- edge weights
- attributed graphs
- planar graphs
- small world
- finding the shortest path
- minimum spanning tree
- neighborhood graph