Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns.
Susheel SureshVinith BuddeJennifer NevillePan LiJianzhu MaPublished in: CoRR (2021)
Keyphrases
- dynamic graph
- neural network
- graph structures
- graph mining
- graph data
- graph patterns
- dense subgraphs
- graph structure
- graph theory
- directed graph
- weighted graph
- graph representation
- graph databases
- labeled graphs
- pattern mining
- frequent subgraphs
- graph clustering
- power laws
- graph matching
- graph model
- structural pattern recognition
- graph construction
- adjacency matrix
- graph search
- graph classification
- query graph
- pattern recognition
- community detection
- spanning tree
- graph properties
- graph theoretic
- bipartite graph
- real world graphs
- graph partitioning
- community discovery
- undirected graph
- subgraph isomorphism
- random graphs
- graph isomorphism
- graph theoretical
- series parallel
- structural patterns
- neighborhood graph
- minimum spanning tree
- pattern discovery
- reachability queries
- polynomial time complexity
- community structure
- artificial neural networks
- evolving graphs
- finding the shortest path
- graph kernels
- surprising patterns
- temporal sequences
- average degree
- maximum clique
- graph representations
- topological information
- clustering coefficient
- proximity graph
- connected components
- structured data
- directed acyclic
- planar graphs
- real world networks
- connected graphs