Discovering Boundary Values of Feature-based Machine Learning Classifiers through Exploratory Datamorphic Testing
This work addresses the problem of understanding and testing machine learning behavior for software testers, presenting incremental improvements in testing methodologies.
The paper tackles the difficulty of testing AI applications by proposing exploratory datamorphic testing strategies to discover class boundaries in machine learning classifiers, evaluating their capability and cost through controlled experiments and case studies.
Testing has been widely recognised as difficult for AI applications. This paper proposes a set of testing strategies for testing machine learning applications in the framework of the datamorphism testing methodology. In these strategies, testing aims at exploring the data space of a classification or clustering application to discover the boundaries between classes that the machine learning application defines. This enables the tester to understand precisely the behaviour and function of the software under test. In the paper, three variants of exploratory strategies are presented with the algorithms implemented in the automated datamorphic testing tool Morphy. The correctness of these algorithms are formally proved. Their capability and cost of discovering borders between classes are evaluated via a set of controlled experiments with manually designed subjects and a set of case studies with real machine learning models.