Shift Happens: Adjusting Classifiers

TL;DR

This paper introduces methods to adjust probabilistic classifiers for dataset shift by transforming predictions to better match new class distributions, with theoretical guarantees and experimental validation.

Contribution

It proposes unbounded and bounded adjustment methods that improve classifier calibration under dataset shift, extending proper scoring rule minimization.

Findings

Methods reduce loss when class distribution is known

Adjustments improve performance under approximate class distribution knowledge

Theoretical guarantees support practical effectiveness

Abstract

Minimizing expected loss measured by a proper scoring rule, such as Brier score or log-loss (cross-entropy), is a common objective while training a probabilistic classifier. If the data have experienced dataset shift where the class distributions change post-training, then often the model's performance will decrease, over-estimating the probabilities of some classes while under-estimating the others on average. We propose unbounded and bounded general adjustment (UGA and BGA) methods that transform all predictions to (re-)equalize the average prediction and the class distribution. These methods act differently depending on which proper scoring rule is to be minimized, and we have a theoretical guarantee of reducing loss on test data, if the exact class distribution is known. We also demonstrate experimentally that, when in practice the class distribution is known only approximately, there is often still a reduction in loss depending on the amount of shift and the precision to which the class distribution is known.