Fast hyperparameter selection for graph kernels via subsampling and multiple kernel learning.
Michele DoniniNicolò NavarinIvano LauriolaFabio AiolliFabrizio CostaPublished in: ESANN (2017)
Keyphrases
- multiple kernel learning
- graph kernels
- kernel methods
- kernel machines
- gaussian processes
- kernel function
- kernel learning
- multi task
- support vector
- learning problems
- linear combination
- semi supervised learning
- support vectors
- feature selection
- hyperparameters
- support vector machine
- kernel matrix
- multi class
- binary classification
- transfer learning
- data sets
- support vector regression
- gaussian process
- feature space
- machine learning