Callisto: Entropy based test generation and data quality assessment for Machine Learning Systems
This addresses the need for robust validation in ML systems, particularly for detecting errors and low-quality data, though it appears incremental as it builds on existing testing concepts with a novel uncertainty-based approach.
The paper tackles the problem of validating ML-based systems by proposing CALLISTO, a blackbox test generation and data quality assessment framework that leverages prediction uncertainty, revealing thousands of errors in real-world datasets and increasing erroneous test cases by up to a factor of 20 compared to methods without such knowledge.
Machine Learning (ML) has seen massive progress in the last decade and as a result, there is a pressing need for validating ML-based systems. To this end, we propose, design and evaluate CALLISTO - a novel test generation and data quality assessment framework. To the best of our knowledge, CALLISTO is the first blackbox framework to leverage the uncertainty in the prediction and systematically generate new test cases for ML classifiers. Our evaluation of CALLISTO on four real world data sets reveals thousands of errors. We also show that leveraging the uncertainty in prediction can increase the number of erroneous test cases up to a factor of 20, as compared to when no such knowledge is used for testing. CALLISTO has the capability to detect low quality data in the datasets that may contain mislabelled data. We conduct and present an extensive user study to validate the results of CALLISTO on identifying low quality data from four state-of-the-art real world datasets.