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