Rectifying Group Irregularities in Explanations for Distribution Shift
This addresses interpretability issues in distribution shift for machine learning practitioners, though it appears incremental as it builds on existing shift explanation methods.
The paper tackles the problem of distribution shift explanations introducing group irregularities, proposing Group-aware Shift Explanations (GSE) to maintain group structures and enhance feasibility and robustness across tabular, language, and image settings.
It is well-known that real-world changes constituting distribution shift adversely affect model performance. How to characterize those changes in an interpretable manner is poorly understood. Existing techniques to address this problem take the form of shift explanations that elucidate how to map samples from the original distribution toward the shifted one by reducing the disparity between these two distributions. However, these methods can introduce group irregularities, leading to explanations that are less feasible and robust. To address these issues, we propose Group-aware Shift Explanations (GSE), a method that produces interpretable explanations by leveraging worst-group optimization to rectify group irregularities. We demonstrate how GSE not only maintains group structures, such as demographic and hierarchical subpopulations, but also enhances feasibility and robustness in the resulting explanations in a wide range of tabular, language, and image settings.