Calibrated Explanations for Multi-Class

EasyChair Preprint no. 14106

Abstract

Calibrated Explanations is a recently proposed feature importance explanation method providing uncertainty quantifications. It utilises Venn-Abers to generate well-calibrated factual and counterfactual explanations for binary classification. In this paper, we extend the method to support multi-class classification. The paper includes an evaluation illustrating the calibration quality of the selected multi-class calibration approach, as well as a demonstration of how the explanations can help determine which explanations to trust.

Keyphrases: Calibrated Explanations, multi-class, Venn-Abers, XAI

@Booklet{EasyChair:14106,
  author = {Tuwe Löfström and Helena Löfström and Ulf Johansson},
  title = {Calibrated Explanations for Multi-Class},
  howpublished = {EasyChair Preprint no. 14106},

  year = {EasyChair, 2024}}