How does Heterophily Impact the Robustness of Graph Neural Networks?: Theoretical Connections and Practical Implications.
Jiong ZhuJunchen JinDonald LovelandMichael T. SchaubDanai KoutraPublished in: KDD (2022)
Keyphrases
- neural network
- graph representation
- graph theory
- neural network model
- pattern recognition
- fault diagnosis
- random walk
- graph theoretic
- connected components
- directed graph
- multi layer
- multilayer perceptron
- stable set
- graph based algorithm
- graph search
- graph model
- link analysis
- graph matching
- self organizing maps
- back propagation
- theoretical analysis
- artificial neural networks
- recurrent neural networks
- bayesian networks
- data sets
- radial basis function
- data mining
- adjacency matrix
- high robustness