Group lasso regularized multiple kernel learning for heterogeneous feature selection.
Yi-Ren YehYung-Yu ChungTing-Chu LinYu-Chiang Frank WangPublished in: IJCNN (2011)
Keyphrases
- multiple kernel learning
- group lasso
- feature selection
- multi task
- variable selection
- convex relaxation
- support vector
- linear combination
- text categorization
- least squares
- learning problems
- kernel methods
- multi task learning
- high dimensionality
- multi class
- feature set
- text classification
- semi supervised learning
- feature space
- dimensionality reduction
- information gain
- feature subset
- regression model
- model selection
- kernel function
- naive bayes
- classification accuracy
- binary classification
- small number
- cost sensitive
- classification models
- data sets
- support vector machine
- unsupervised learning
- decision trees
- machine learning