HP-GMN: Graph Memory Networks for Heterophilous Graphs.
Junjie XuEnyan DaiXiang ZhangSuhang WangPublished in: CoRR (2022)
Keyphrases
- graph structures
- average degree
- real world graphs
- graph structure
- graph theory
- highly connected
- community discovery
- edge weights
- graph layout
- small world
- weighted graph
- dynamic networks
- graph representation
- graph mining
- disk resident
- social networks
- real world social networks
- graph matching
- graph clustering
- labeled graphs
- social graphs
- fully connected
- directed graph
- graph theoretic
- graph construction
- degree distribution
- graph model
- betweenness centrality
- complex networks
- adjacency matrix
- graph theoretical
- bipartite graph
- random graphs
- connected components
- directed edges
- community detection
- graph databases
- small world networks
- graph partitioning
- series parallel
- graph properties
- graph isomorphism
- minimum spanning tree
- densely connected
- undirected graph
- spanning tree
- random walk
- graph kernels
- graph representations
- network analysis
- graph mining algorithms
- structured data
- protein interaction networks
- real world networks
- maximum cardinality
- structural pattern recognition
- subgraph isomorphism
- graph classification
- dense subgraphs
- graph data
- network structure
- main memory
- reachability queries
- power law
- graph search
- maximal cliques
- clustering coefficient
- attributed graphs
- neighborhood graph
- biological networks
- power law distribution
- finding the shortest path
- social network analysis
- scale free
- topological information
- web graph
- network properties
- bounded treewidth
- massive graphs
- connected graphs