Feature Overcorrelation in Deep Graph Neural Networks: A New Perspective.
Wei JinXiaorui LiuYao MaCharu C. AggarwalJiliang TangPublished in: CoRR (2022)
Keyphrases
- neural network
- back propagation
- graph structure
- random walk
- graph model
- connected components
- pattern recognition
- artificial neural networks
- recurrent neural networks
- vector representation
- structured data
- graph based algorithm
- graph theory
- bipartite graph
- directed graph
- graph representation
- graph theoretic
- neural network model
- activation function
- directed acyclic graph
- neighborhood structure
- weighted graph
- neural nets
- fault diagnosis
- graphical models
- fuzzy logic
- feature vectors
- pairwise
- genetic algorithm
- machine learning