Training Graph Neural Networks on Growing Stochastic Graphs.
Juan CerviñoLuana RuizAlejandro RibeiroPublished in: ICASSP (2023)
Keyphrases
- neural network
- graph theory
- graph representation
- training process
- weighted graph
- training algorithm
- graph structure
- directed graph
- graph matching
- graph theoretic
- graph construction
- graph mining
- graph structures
- labeled graphs
- graph databases
- graph model
- graph theoretical
- graph clustering
- graph search
- feedforward neural networks
- graph partitioning
- random graphs
- graph classification
- bipartite graph
- series parallel
- adjacency matrix
- multi layer perceptron
- feed forward neural networks
- graph representations
- spanning tree
- graph transformation
- dynamic graph
- graph properties
- undirected graph
- subgraph isomorphism
- graph isomorphism
- back propagation
- structural pattern recognition
- pattern recognition
- artificial neural networks
- graph kernels
- graph data
- dense subgraphs
- graph embedding
- edge weights
- connected graphs
- inexact graph matching
- hopfield neural network
- web graph
- attributed graphs
- graph drawing
- adjacency graph
- graph patterns
- connected dominating set
- real world graphs
- directed acyclic
- planar graphs
- training set
- structured data
- neural network model
- polynomial time complexity
- small world
- relational structures
- connected components
- graph layout
- frequent subgraphs
- random walk
- massive graphs
- maximum cardinality
- finding the shortest path
- graphical models
- maximum clique
- maximum common subgraph
- social networks