Fast Sparse GPU Kernels for Accelerated Training of Graph Neural Networks.
Ruibo FanWei WangXiaowen ChuPublished in: IPDPS (2023)
Keyphrases
- neural network
- training process
- training algorithm
- feedforward neural networks
- multi layer perceptron
- feed forward neural networks
- avoid overfitting
- backpropagation algorithm
- fuzzy logic
- gaussian graphical models
- graph representation
- back propagation
- artificial neural networks
- linear svm
- linear combination
- structured data
- training samples
- directed graph
- pattern recognition
- high dimensional
- support vector
- real time
- general purpose
- neural network training
- kernel function
- kernel matrices
- random walk
- error back propagation
- additive models
- neural network model
- elastic net
- gpu implementation
- training data
- multiple kernel
- sparse matrix
- kernel learning
- multiple kernel learning
- graphical models
- gaussian processes
- graph mining
- multi layer
- low rank
- neural nets
- self organizing maps