Testing Monotonicity of Machine Learning Models
This work addresses the need for quality assurance in ML models used in decision-making by providing a method to test monotonicity, particularly for black-box models, which is an incremental improvement over existing techniques.
The paper tackles the problem of verifying monotonicity in black-box machine learning models, which is crucial for quality assurance in decision-making applications, and demonstrates that their verification-based testing method outperforms adaptive random testing and property-based techniques in effectiveness and efficiency on 90 models.
Today, machine learning (ML) models are increasingly applied in decision making. This induces an urgent need for quality assurance of ML models with respect to (often domain-dependent) requirements. Monotonicity is one such requirement. It specifies a software as 'learned' by an ML algorithm to give an increasing prediction with the increase of some attribute values. While there exist multiple ML algorithms for ensuring monotonicity of the generated model, approaches for checking monotonicity, in particular of black-box models, are largely lacking. In this work, we propose verification-based testing of monotonicity, i.e., the formal computation of test inputs on a white-box model via verification technology, and the automatic inference of this approximating white-box model from the black-box model under test. On the white-box model, the space of test inputs can be systematically explored by a directed computation of test cases. The empirical evaluation on 90 black-box models shows verification-based testing can outperform adaptive random testing as well as property-based techniques with respect to effectiveness and efficiency.