Explanatory Model Monitoring to Understand the Effects of Feature Shifts on Performance

Monitoring and maintaining machine learning models are among the most critical challenges in translating recent advances in the field into real-world applications. However, current monitoring methods lack the capability of provide actionable insights answering the question of why the performance of a particular model really degraded. In this work, we propose a novel approach to explain the behavior of a black-box model under feature shifts by attributing an estimated performance change to interpretable input characteristics. We refer to our method that combines concepts from Optimal Transport and Shapley Values as Explanatory Performance Estimation (XPE). We analyze the underlying assumptions and demonstrate the superiority of our approach over several baselines on different Figure 1: Illustration of an opaque vision system subject to data sets across various data modalities such as images, audio, and hardware degradation or environment changes, e.g., speckles tabular data. We also indicate how the generated results can lead on the lens or stray light. Explanatory Performance Estimation to valuable insights, enabling explanatory model monitoring by (XPE) allows to anticipate and explain the resulting performance revealing potential root causes for model deterioration and guiding decrease by highlighting which parts of the shift toward actionable countermeasures.