Minimal Variance Sampling with Provable Guarantees for Fast Training of Graph Neural Networks.
Weilin CongRana ForsatiMahmut T. KandemirMehrdad MahdaviPublished in: CoRR (2020)
Keyphrases
- neural network
- training process
- training algorithm
- feedforward neural networks
- feed forward neural networks
- pattern recognition
- artificial neural networks
- structured data
- multi layer perceptron
- training examples
- multilayer perceptron
- recurrent neural networks
- neural network training
- backpropagation algorithm
- graph representation
- connected components
- supervised learning
- fuzzy logic
- directed graph
- directed acyclic graph
- activation function
- random walk
- training phase
- graph databases
- self organizing maps
- random sampling
- graph structure
- training set
- monte carlo
- feed forward
- graph model
- support vector machine
- social networks
- undirected graph
- spanning tree
- fault diagnosis
- neural nets
- neural network model