The Self-Loop Paradox: Investigating the Impact of Self-Loops on Graph Neural Networks.
Moritz LampertIngo ScholtesPublished in: CoRR (2023)
Keyphrases
- neural network
- pattern recognition
- directed graph
- artificial neural networks
- fuzzy logic
- random walk
- graph theory
- recurrent neural networks
- graph representation
- graph structure
- structured data
- connected components
- directed acyclic graph
- weighted graph
- graph theoretic
- fault diagnosis
- graph matching
- rule extraction
- graph based algorithm
- stable set
- graph partitioning
- training process
- feed forward
- self organizing maps
- graph cuts
- search engine