Skip to content

Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibration

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Original languageEnglish
Title of host publicationNeurIPS 2019
Number of pages12
DateAccepted/In press - 3 Sep 2019

Abstract

Class probabilities predicted by most multiclass classifiers are uncalibrated, often tending towards over-confidence. With neural networks, calibration can be improved by temperature scaling, a method to learn a single corrective multiplicative factor for inputs to the last softmax layer. On non-neural models the existing methods apply binary calibration in a pairwise or one-vs-rest fashion. We propose a natively multiclass calibration method applicable to classifiers from any model class, derived from Dirichlet distributions and generalising the beta calibration method from binary classification. It is easily implemented with neural nets since it is equivalent to log-transforming the uncalibrated probabilities, followed by one linear layer and softmax. Experiments demonstrate improved probabilistic predictions according to multiple measures (confidence-ECE, classwise-ECE, log-loss, Brier score) across a wide range of datasets and classifiers. Parameters of the learned Dirichlet calibration map provide insights to the biases in the uncalibrated model.

    Structured keywords

  • Digital Health

Documents

Documents

  • Full-text PDF (author’s accepted manuscript)

    Accepted author manuscript, 323 KB, PDF document

    Embargo ends: 1/01/99

    Request copy

View research connections

Related faculties, schools or groups