Increase and Conquer: Training Graph Neural Networks on Growing Graphs.
Juan CerviñoLuana RuizAlejandro RibeiroPublished in: CoRR (2021)
Keyphrases
- neural network
- graph representation
- graph structure
- graph matching
- directed graph
- training process
- graph theory
- graph construction
- graph model
- training algorithm
- weighted graph
- labeled graphs
- graph mining
- graph theoretic
- graph classification
- graph databases
- series parallel
- graph structures
- graph partitioning
- multi layer perceptron
- adjacency matrix
- subgraph isomorphism
- graph data
- structural pattern recognition
- graph theoretical
- graph transformation
- graph search
- graph clustering
- undirected graph
- graph isomorphism
- feedforward neural networks
- random graphs
- pattern recognition
- bipartite graph
- back propagation
- graph kernels
- maximum common subgraph
- feed forward neural networks
- spanning tree
- graph patterns
- edge weights
- reachability queries
- graph properties
- connected dominating set
- evolving graphs
- training set
- dense subgraphs
- random walk
- adjacency graph
- planar graphs
- pattern mining
- maximum clique
- graphical structure
- minimum spanning tree
- attributed relational graph
- inexact graph matching
- connected graphs
- frequent subgraphs
- web graph
- dynamic graph
- polynomial time complexity
- attributed graphs
- graph drawing
- community discovery
- proximity graph
- artificial neural networks
- directed acyclic
- neighborhood graph
- finding the shortest path
- recurrent neural networks
- query graph
- small world
- graph representations