Unsupervised Heterogeneous Graph Neural Networks for One-Class Tasks: Exploring Early Fusion Operators.
Marcos Paulo Silva GôloMarcelo Isaias de MoraesRudinei GoularteRicardo Marcondes MarcaciniPublished in: J. Interact. Syst. (2024)
Keyphrases
- neural network
- genetic algorithm
- artificial neural networks
- semi supervised
- random walk
- pattern recognition
- weighted graph
- unsupervised methods
- competitive learning
- graph theoretic
- fusion method
- fault diagnosis
- graph partitioning
- graph matching
- graph structure
- directed graph
- graph theory
- multi sensor
- recurrent neural networks
- data fusion
- back propagation
- shortest path
- unsupervised learning
- machine learning