MAAT: a novel ensemble approach to addressing fairness and performance bugs for machine learning software.
Zhenpeng ChenJie M. ZhangFederica SarroMark HarmanPublished in: ESEC/SIGSOFT FSE (2022)
Keyphrases
- machine learning
- software systems
- source code
- bug localization
- software tools
- test cases
- software projects
- software development
- development process
- root cause
- software design
- machine learning algorithms
- learning algorithm
- active learning
- explanation based learning
- computer vision
- machine learning methods
- pattern recognition
- feature selection
- learning systems
- software architecture
- website
- artificial intelligence
- machine learning approaches
- security vulnerabilities
- maintenance activities
- natural language processing
- static analysis
- software evolution
- supervised learning
- information extraction
- hardware design
- test suite
- text mining
- decision trees