MixCode: Enhancing Code Classification by Mixup-Based Data Augmentation.
Zeming DongQiang HuYuejun GuoMaxime CordyMike PapadakisZhenya ZhangYves Le TraonJianjun ZhaoPublished in: SANER (2023)
Keyphrases
- data sets
- data collection
- statistical analysis
- data sources
- raw data
- pattern recognition
- training data
- high quality
- synthetic data
- original data
- database
- small number
- data points
- classification scheme
- data processing
- missing data
- experimental data
- preprocessing
- data analysis
- data quality
- spatial data
- classification models
- pattern classification
- training dataset
- labeled data
- input data
- image classification
- nearest neighbor
- data model
- prior knowledge
- support vector
- decision trees
- machine learning
- data mining
- neural network
- databases