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: NeurIPS (2023)
Keyphrases
- neural network
- directed graph
- graph structure
- pattern recognition
- decision trees
- undirected graph
- tree structure
- pattern classification
- rule extraction
- classification accuracy
- support vector
- feature selection
- learning vector quantization
- neural networks and support vector machines
- classification method
- classification algorithm
- finding the shortest path
- random walk
- image classification
- multi class
- feature space
- supervised learning
- neural network model
- support vector machine
- directed acyclic graph
- knn
- graph representation
- feature vectors
- root node
- betweenness centrality
- feature extraction
- machine learning