Debugging Machine Learning via Model Assertions

Machine learning models are being deployed in mission-critical settings, such as self-driving cars. However, these models can fail in complex ways, so it is imperative that application developers find ways to debug these models. We propose adapting software assertions, or boolean statements about the state of a program that must be true, to the task of debugging ML models. With model assertions, ML developers can specify constraints on model outputs, e.g., cars should not disappear and reappear in successive frames of a video. We propose several ways to use model assertions in ML debugging, including use in runtime monitoring, in performing corrective actions, and in collecting “hard examples” to further train models with human labeling or weak supervision. We show that, for a video analytics task, simple assertions can effectively find errors and correction rules can effectively correct model output (up to 100% and 90% respectively). We additionally collect and label parts of video where assertions fire (as a form of active learning) and show that this procedure can improve model performance by up to 2×.