Document worth reading: “Machine Learning Testing: Survey, Landscapes and Horizons”

This paper provides an entire survey of Machine Learning Testing (ML testing) evaluation. It covers 128 papers on testing properties (e.g., correctness, robustness, and fairness), testing components (e.g., the data, finding out program, and framework), testing workflow (e.g., test know-how and test evaluation), and software program conditions (e.g., autonomous driving, machine translation). The paper moreover analyses developments concerning datasets, evaluation developments, and evaluation focus, concluding with evaluation challenges and promising evaluation directions in ML testing. Machine Learning Testing: Survey, Landscapes and Horizons