The Curse of Class Imbalance and Conflicting Metrics with Machine Learning for Side-channel Evaluations.
Stjepan PicekAnnelie HeuserAlan JovicShivam BhasinFrancesco RegazzoniPublished in: IACR Cryptol. ePrint Arch. (2018)
Keyphrases
- class imbalance
- machine learning
- software defect prediction
- active learning
- high dimensionality
- cost sensitive learning
- class distribution
- feature selection
- cost sensitive
- imbalanced datasets
- high dimensional
- high dimensional data
- majority class
- machine learning methods
- machine learning algorithms
- concept drift
- small disjuncts
- learning algorithm
- feature ranking
- dimensionality reduction
- sampling methods
- pattern recognition
- data mining
- misclassification costs
- reinforcement learning
- supervised learning
- feature space
- random sampling
- ensemble learning
- bayesian networks
- text classification
- training set
- imbalanced class distribution
- learning tasks
- test data
- data sets
- unsupervised learning
- decision trees
- semi supervised
- support vector machine
- prior knowledge