Enhancing Code Classification by Mixup-Based Data Augmentation.
Zeming DongQiang HuYuejun GuoMaxime CordyMike PapadakisYves Le TraonJianjun ZhaoPublished in: CoRR (2022)
Keyphrases
- raw data
- data analysis
- database
- data sets
- data processing
- data distribution
- feature space
- high quality
- decision trees
- data structure
- training data
- data quality
- original data
- classification accuracy
- machine learning
- neural network
- data collection
- computer systems
- training dataset
- image classification
- classification method
- classification trees
- classification algorithm
- synthetic data
- high dimensional data
- small number
- knn
- prior knowledge
- feature vectors
- pattern recognition
- support vector