Calibrated Selective Classification

Adam Fisch, Tommi S. Jaakkola, Regina Barzilay

Abstract: Selective classification allows models to abstain from making predictions (e.g., say ``I don't know'') when in doubt in order to obtain better effective accuracy. While typical selective models can succeed at producing more accurate predictions on average, they may still allow for wrong predictions that have high confidence, or skip correct predictions that have low confidence. Providing calibrated uncertainty estimates alongside predictions---probabilities that correspond to true frequencies---can be as important as having predictions that are simply accurate on average. Uncertainty estimates, however, can sometimes be unreliable. In this paper, we develop a new approach to selective classification in which we propose a method for rejecting examples with ``uncertain'' uncertainties. By doing so, we aim to make predictions with well-calibrated uncertainty estimates over the distribution of accepted examples, a property we call selective calibration. We present a framework for learning selectively calibrated models, where a separate selector network is trained to improve the selective calibration error of a given base model. In particular, our work focuses on achieving robust calibration, where the model is intentionally designed to be tested on out-of-domain data. We achieve this through a training strategy inspired by distributionally robust optimization, in which we apply simulated input perturbations to the known, in-domain training data. We demonstrate the empirical effectiveness of our approach on multiple image classification and lung cancer risk assessment tasks.

Submission Length: Regular submission (no more than 12 pages of main content)

Previous TMLR Submission Url: https://openreview.net/forum?id=4vrbt6sHfz

Changes Since Last Submission:

A \usepackage{times} had accidentally been included in the previous submission .tex file, causing the wrong font to be used. The current submission has been updated to follow the correct style.

Uploaded revision incorporates changes per reviewer comments.

Code: https://github.com/ajfisch/calibrated-selective-classification

Assigned Action Editor: ~Tom_Rainforth1

License: Creative Commons Attribution 4.0 International (CC BY 4.0)

Submission Number: 411