EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs.
Aldo ParejaGiacomo DomeniconiJie ChenTengfei MaToyotaro SuzumuraHiroki KanezashiTim KalerCharles E. LeisersonPublished in: CoRR (2019)
Keyphrases
- dynamic networks
- dynamic graph
- evolving graphs
- graph theory
- graph structures
- graph representation
- edge weights
- average degree
- graph clustering
- graph structure
- network analysis
- graph theoretic
- community discovery
- weighted graph
- highly connected
- graph layout
- real world graphs
- social networks
- graph databases
- directed graph
- network structure
- graph theoretical
- labeled graphs
- small world
- graph construction
- graph matching
- graph search
- fully connected
- real world social networks
- degree distribution
- social graphs
- complex networks
- graph partitioning
- bipartite graph
- graph mining
- graph model
- betweenness centrality
- graph data
- undirected graph
- structural pattern recognition
- real world networks
- spanning tree
- maximal cliques
- random graphs
- biological networks
- structured data
- graph classification
- random walk
- adjacency matrix
- social network analysis
- maximum clique
- graph properties
- graph representations
- graph isomorphism
- graph kernels
- minimum spanning tree
- network properties
- attributed graphs
- series parallel
- protein interaction networks
- reachability queries
- dense subgraphs
- graph patterns
- maximum common subgraph