BNS-GCN: Efficient Full-Graph Training of Graph Convolutional Networks with Partition-Parallelism and Random Boundary Node Sampling.
Cheng WanYoujie LiAng LiNam Sung KimYingyan LinPublished in: CoRR (2022)
Keyphrases
- graph structure
- directed graph
- edge weights
- overlapping communities
- graph theory
- directed acyclic graph
- random walk
- random graphs
- weighted graph
- graph partitioning
- undirected graph
- bayesian networks
- partitioning algorithm
- community discovery
- path length
- spanning tree
- bipartite graph
- complex networks
- betweenness centrality
- nodes of a graph
- clique tree
- degree distribution
- heterogeneous social networks
- parallel execution
- deep learning
- network analysis
- random variables
- shortest path
- graphical models