Unifying over-smoothing and over-squashing in graph neural networks: A physics informed approach and beyond.
Zhiqi ShaoDai ShiAndi HanYi GuoQibin ZhaoJunbin GaoPublished in: CoRR (2023)
Keyphrases
- neural network
- graph representation
- pattern recognition
- multi layer
- graph theory
- graph structure
- random walk
- artificial neural networks
- genetic algorithm
- graph databases
- directed graph
- graph matching
- fuzzy logic
- structured data
- computer science
- connected components
- neural network model
- graph model
- weighted graph
- smoothing algorithm
- bipartite graph
- neural nets
- image processing
- machine learning
- fault diagnosis
- fuzzy systems
- directed acyclic graph
- denoising
- expert systems
- spanning tree
- dependency graph
- smoothing methods
- graph based algorithm