When Do Graph Neural Networks Help with Node Classification: Investigating the Homophily Principle on Node Distinguishability.
Sitao LuanChenqing HuaMinkai XuQincheng LuJiaqi ZhuXiao-Wen ChangJie FuJure LeskovecDoina PrecupPublished in: CoRR (2023)
Keyphrases
- neural network
- graph structure
- pattern recognition
- directed graph
- decision trees
- tree structure
- machine learning
- overlapping communities
- supervised learning
- genetic algorithm
- connected components
- classification method
- feature vectors
- edge weights
- graph representation
- weighted graph
- feature extraction
- support vector
- training set
- class labels
- image classification
- graphical models
- feature selection
- pattern classification
- graph theory
- social networks
- feature set
- classification scheme
- classification accuracy
- rule extraction
- root node