Improving the Robustness of Graphs through Reinforcement Learning and Graph Neural Networks.
Victor-Alexandru DarvariuStephen HailesMirco MusolesiPublished in: CoRR (2020)
Keyphrases
- neural network
- reinforcement learning
- graph representation
- graph theory
- graph structure
- graph matching
- weighted graph
- directed graph
- graph theoretic
- graph construction
- graph classification
- graph databases
- graph mining
- labeled graphs
- graph theoretical
- adjacency matrix
- graph structures
- graph model
- graph search
- graph properties
- graph clustering
- random graphs
- series parallel
- graph partitioning
- maximum clique
- bipartite graph
- undirected graph
- graph transformation
- graph data
- pattern recognition
- reachability queries
- subgraph isomorphism
- dynamic graph
- inexact graph matching
- state space
- function approximation
- graph patterns
- graph isomorphism
- graph drawing
- maximal cliques
- learning classifier systems
- attributed graphs
- connected graphs
- maximum common subgraph
- structural pattern recognition
- directed acyclic
- graph representations
- social graphs
- artificial neural networks
- random walk
- evolving graphs
- planar graphs
- pattern mining
- spanning tree
- finding the shortest path
- graph kernels
- maximum cardinality
- real world graphs
- connected dominating set
- proximity graph
- adjacency graph
- topological information
- graph embedding
- neighborhood graph
- edge weights
- back propagation
- quasi cliques
- relational structures
- graph layout
- dense subgraphs
- community discovery
- function approximators
- minimum spanning tree
- small world
- web graph
- markov decision processes
- machine learning
- bounded treewidth
- massive graphs
- directed acyclic graph
- complex networks