Materialization optimizations for feature selection workloads.
Ce ZhangArun KumarChristopher RéPublished in: SIGMOD Conference (2014)
Keyphrases
- feature selection
- mutual information
- text categorization
- computer systems
- database systems
- distributed databases
- multi class
- text classification
- feature space
- feature set
- feature selection algorithms
- dimensionality reduction
- method for feature selection
- machine learning
- classification accuracy
- high dimensionality
- multi task
- information gain
- selecting relevant features
- small sample
- selected features
- irrelevant features
- materialized views
- feature subset
- data warehouse
- feature extraction
- classification models
- microarray data
- data warehousing
- information sources
- data processing
- data analysis
- support vector