Timezone: »

Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift
Stephan Rabanser · Stephan Günnemann · Zachary Lipton

Thu Dec 12 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #54

We might hope that when faced with unexpected inputs, well-designed software systems would fire off warnings. Machine learning (ML) systems, however, which depend strongly on properties of their inputs (e.g. the i.i.d. assumption), tend to fail silently. This paper explores the problem of building ML systems that fail loudly, investigating methods for detecting dataset shift, identifying exemplars that most typify the shift, and quantifying shift malignancy. We focus on several datasets and various perturbations to both covariates and label distributions with varying magnitudes and fractions of data affected. Interestingly, we show that across the dataset shifts that we explore, a two-sample-testing-based approach, using pre-trained classifiers for dimensionality reduction, performs best. Moreover, we demonstrate that domain-discriminating approaches tend to be helpful for characterizing shifts qualitatively and determining if they are harmful.

Author Information

Stephan Rabanser (Amazon AWS AI Labs)
Stephan Günnemann (Technical University of Munich)
Zachary Lipton (Carnegie Mellon University)

More from the Same Authors