Schema-Aware Deep Graph Convolutional Networks for Heterogeneous Graphs.
Saurav ManchandaDa ZhengGeorge KarypisPublished in: IEEE BigData (2021)
Keyphrases
- graph structures
- average degree
- highly connected
- real world graphs
- edge weights
- graph representation
- graph layout
- graph theory
- dynamic networks
- graph clustering
- graph structure
- graph mining
- directed graph
- deep learning
- small world
- community discovery
- weighted graph
- social graphs
- graph matching
- random graphs
- community detection
- fully connected
- real world social networks
- graph theoretic
- labeled graphs
- graph construction
- social networks
- protein interaction networks
- adjacency matrix
- graph databases
- graph model
- complex networks
- graph classification
- degree distribution
- graph theoretical
- massive graphs
- network analysis
- series parallel
- spanning tree
- bipartite graph
- betweenness centrality
- graph data
- heterogeneous networks
- graph partitioning
- undirected graph
- graph representations
- graph search
- random walk
- connected components
- graph properties
- densely connected
- reachability queries
- structural pattern recognition
- graph mining algorithms
- dynamic graph
- graph isomorphism
- planar graphs
- small world networks
- biological networks
- directed edges
- structured data
- functional modules
- neighborhood graph
- community structure
- link prediction
- scale free
- attributed graphs
- shortest path
- social network analysis
- network structure
- real world networks
- graph kernels
- graph patterns
- maximum clique
- maximal cliques
- subgraph isomorphism
- connected graphs
- unsupervised feature learning
- data model
- finding the shortest path
- data sources
- directed acyclic graph
- power law
- deep belief networks
- network properties