Can Graph Neural Networks Go Deeper Without Over-Smoothing? Yes, With a Randomized Path Exploration!
Kushal BoseSwagatam DasPublished in: IEEE Trans. Emerg. Top. Comput. Intell. (2023)
Keyphrases
- neural network
- pattern recognition
- solution path
- shortest path
- graph model
- artificial neural networks
- graph theoretic
- graph matching
- path length
- graph theory
- shortest path problem
- neural network model
- bipartite graph
- graph representation
- graph databases
- strongly connected
- hamiltonian path
- graph structure
- lower bound
- fuzzy systems
- graph mining
- feed forward
- activation function
- connected components
- random walk
- fuzzy logic
- mobile robot
- social networks
- information retrieval