Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labeled Nodes.
Ke SunZhouchen LinZhanxing ZhuPublished in: AAAI (2020)
Keyphrases
- multistage
- fully connected
- directed graph
- graph structure
- graph structures
- average degree
- supervised learning
- weighted graph
- small world
- undirected graph
- edge weights
- social graphs
- graph clustering
- labeled graphs
- directed edges
- learning algorithm
- graph representation
- network structure
- dynamic programming
- production system
- connected graphs
- graphical models
- shortest path
- spanning tree
- attack detection
- interconnection networks
- np hard
- betweenness centrality
- real world graphs
- random walk
- optimal policy
- graph construction
- random graphs
- graph theory