EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs.
Aldo ParejaGiacomo DomeniconiJie ChenTengfei MaToyotaro SuzumuraHiroki KanezashiTim KalerTao B. SchardlCharles E. LeisersonPublished in: AAAI (2020)
Keyphrases
- dynamic networks
- dynamic graph
- evolving graphs
- graph structures
- highly connected
- edge weights
- graph theory
- average degree
- graph matching
- directed graph
- weighted graph
- graph mining
- real world graphs
- graph theoretic
- graph representation
- small world
- graph model
- graph structure
- graph databases
- network structure
- graph layout
- graph construction
- random graphs
- network analysis
- social graphs
- minimum spanning tree
- graph clustering
- graph search
- fully connected
- graph properties
- graph partitioning
- connected components
- graph classification
- structured data
- community discovery
- series parallel
- directed edges
- graph representations
- subgraph isomorphism
- spanning tree
- community detection
- protein interaction networks
- graph theoretical
- adjacency matrix
- bipartite graph
- social networks
- densely connected
- dense subgraphs
- maximum common subgraph
- betweenness centrality
- degree distribution
- random walk
- maximum clique
- planar graphs
- bounded treewidth
- frequent subgraphs
- reachability queries
- biological networks
- undirected graph
- structural pattern recognition
- real world social networks
- directed acyclic graph
- finding the shortest path
- graph mining algorithms
- graphical models