Machine Learning Testing: Survey, Landscapes and Horizons
Machine Learning Testing: Survey, Landscapes and Horizons
复制标题
DOI：
10.1109/tse.2019.2962027
复制
发表时间：
2019-06
影响因子：
7.4
通讯作者：
J Zhang;M. Harman;Lei Ma;Yang Liu
中科院分区：
文献类型：
--
作者：
J Zhang;M. Harman;Lei Ma;Yang Liu
本文提供了测试机器学习系统的技术的全面调查；机器学习测试（ML测试）研究。它涵盖了144篇关于测试属性（例如，正确性、健壮性和公平性）、测试组件（例如，数据、学习程序和框架）、测试工作流（例如，测试生成和测试评估）和应用场景（例如，自动驾驶、机器翻译）的论文。本文还分析了机器学习测试的数据集、研究趋势和研究重点，总结了机器学习测试的研究挑战和研究方向。
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.