Estimating and Explaining Model Performance When Both Covariates and Labels Shift
This addresses the challenge of reliable ML deployment under flexible distribution shifts, with incremental contributions by unifying and generalizing existing shift models.
The paper tackles the problem of estimating model performance on new data when both covariates and labels shift, proposing the Sparse Joint Shift (SJS) model and SEES framework, which achieves up to an order of magnitude improvement in shift estimation error over existing methods.
Deployed machine learning (ML) models often encounter new user data that differs from their training data. Therefore, estimating how well a given model might perform on the new data is an important step toward reliable ML applications. This is very challenging, however, as the data distribution can change in flexible ways, and we may not have any labels on the new data, which is often the case in monitoring settings. In this paper, we propose a new distribution shift model, Sparse Joint Shift (SJS), which considers the joint shift of both labels and a few features. This unifies and generalizes several existing shift models including label shift and sparse covariate shift, where only marginal feature or label distribution shifts are considered. We describe mathematical conditions under which SJS is identifiable. We further propose SEES, an algorithmic framework to characterize the distribution shift under SJS and to estimate a model's performance on new data without any labels. We conduct extensive experiments on several real-world datasets with various ML models. Across different datasets and distribution shifts, SEES achieves significant (up to an order of magnitude) shift estimation error improvements over existing approaches.