Confidence Calibration for Domain Generalization under Covariate Shift
This addresses calibration issues for machine learning models in real-world applications where target domain data is unavailable, though it is incremental as it builds on existing domain adaptation approaches.
The paper tackles the problem of confidence calibration under covariate shift by proposing domain generalization methods that use multiple calibration domains without requiring target domain data, resulting in an 8.86 percentage point decrease in expected calibration error on the Office-Home dataset.
Existing calibration algorithms address the problem of covariate shift via unsupervised domain adaptation. However, these methods suffer from the following limitations: 1) they require unlabeled data from the target domain, which may not be available at the stage of calibration in real-world applications and 2) their performance depends heavily on the disparity between the distributions of the source and target domains. To address these two limitations, we present novel calibration solutions via domain generalization. Our core idea is to leverage multiple calibration domains to reduce the effective distribution disparity between the target and calibration domains for improved calibration transfer without needing any data from the target domain. We provide theoretical justification and empirical experimental results to demonstrate the effectiveness of our proposed algorithms. Compared against state-of-the-art calibration methods designed for domain adaptation, we observe a decrease of 8.86 percentage points in expected calibration error or, equivalently, an increase of 35 percentage points in improvement ratio for multi-class classification on the Office-Home dataset.