Machine Learning Testing: Survey, Landscapes and Horizons

This paper provides a comprehensive survey of techniques for testing machine learning systems; Machine Learning Testing (ML testing) research. It covers 144 papers on testing properties (e.g., correctness, robustness, and fairness), testing components (e.g., the data, learning program, and framework...

Full description

Saved in:
Bibliographic Details
Published inIEEE transactions on software engineering Vol. 48; no. 1; pp. 1 - 36
Main Authors Zhang, Jie M., Harman, Mark, Ma, Lei, Liu, Yang
Format Journal Article
LanguageEnglish
Published New York IEEE 01.01.2022
IEEE Computer Society
Subjects
Data models
deep neural network
Learning programs
Machine learning
Machine translation
Robustness
Software engineering
Software testing
Training data
Trends
Workflow
Online AccessGet full text

Cover

More Information
Summary:This paper provides a comprehensive survey of techniques for testing machine learning systems; Machine Learning Testing (ML testing) research. It covers 144 papers on testing properties (e.g., correctness, robustness, and fairness), testing components (e.g., the data, learning program, and framework), testing workflow (e.g., test generation and test evaluation), and application scenarios (e.g., autonomous driving, machine translation). The paper also analyses trends concerning datasets, research trends, and research focus, concluding with research challenges and promising research directions in ML testing.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0098-5589
1939-3520
DOI:10.1109/TSE.2019.2962027