GraphHI: Boosting Graph Neural Networks for Large-Scale Graphs.
Hao FengChaokun WangZiyang LiuYunkai LouZhenyu LiuXiaokun ZhuYongjun BaoWeipeng YanPublished in: ICDE (2024)
Keyphrases
- neural network
- massive graphs
- graph representation
- graph matching
- weighted graph
- graph theory
- graph structure
- graph mining
- graph construction
- graph databases
- directed graph
- graph model
- graph theoretical
- adjacency matrix
- graph theoretic
- graph classification
- labeled graphs
- graph isomorphism
- graph properties
- pattern recognition
- series parallel
- random graphs
- graph clustering
- subgraph isomorphism
- graph search
- graph structures
- structural pattern recognition
- graph data
- graph partitioning
- spanning tree
- undirected graph
- graph representations
- bipartite graph
- graph transformation
- reachability queries
- real world graphs
- connected dominating set
- graph embedding
- graph patterns
- evolving graphs
- small world
- dynamic graph
- graph drawing
- community detection
- adjacency graph
- attributed graphs
- planar graphs
- connected graphs
- graph kernels
- bounded treewidth
- minimum spanning tree
- edge weights
- maximum cardinality
- feature selection
- graph mining algorithms
- maximum common subgraph
- neighborhood graph
- artificial neural networks
- graph layout
- connected components
- dense subgraphs
- directed acyclic
- finding the shortest path
- social graphs
- structured data
- frequent subgraphs
- web graph
- topological information
- maximal cliques
- community discovery
- random walk
- proximity graph
- polynomial time complexity
- maximum clique
- query graph
- weak learners
- learning algorithm