Data Debugging with Shapley Importance over Machine Learning Pipelines.
Bojan KarlasDavid DaoMatteo InterlandiSebastian SchelterWentao WuCe ZhangPublished in: ICLR (2024)
Keyphrases
- machine learning
- data analysis
- knowledge discovery
- data sets
- computer systems
- complex data
- synthetic data
- data structure
- data collection
- data distribution
- probability distribution
- image data
- data mining techniques
- data processing
- sensor data
- machine learning algorithms
- database
- prior knowledge
- original data
- machine learning methods
- neural network
- statistical analysis
- computer vision
- small number
- data points
- end users