An Empirical Evaluation of the Effect of Adversarial Labels on Classifier Accuracy Estimation.
Alexandra CliffordCassian CoreyJohn T. HolodnakPublished in: FLAIRS Conference (2019)
Keyphrases
- training data
- unseen data
- label noise
- fold cross validation
- training examples
- class labels
- confusion matrix
- estimation accuracy
- labeled instances
- prediction accuracy
- high accuracy
- higher classification accuracy
- classification rate
- classification accuracy
- training set
- labeling effort
- classification process
- individual classifiers
- support vector machine classifier
- roc curve
- error rate
- fully supervised
- support vector machine
- computational cost
- active learning
- supervised classifiers
- data sets
- annotation effort
- estimation error
- unlabeled data
- semi supervised
- multi agent
- decision trees
- feature selection
- learning algorithm