GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings.
Matthias FeyJan Eric LenssenFrank WeichertJure LeskovecPublished in: CoRR (2021)
Keyphrases
- neural network
- pattern recognition
- artificial neural networks
- graph theory
- connected components
- bipartite graph
- graph representation
- weighted graph
- graph structure
- neural nets
- directed graph
- self organizing maps
- random walk
- fuzzy logic
- historical data
- graph model
- web scale
- graph mining algorithms
- dimensionality reduction
- recurrent neural networks
- graph matching
- multi layer
- fault diagnosis
- activation function
- distance measure
- graph data
- highly scalable
- graph clustering
- hopfield neural network
- bayesian networks