Learning from Exemplary Explanations

TL;DR

This paper introduces a new method for Explanation Based Learning in medical image classification that reduces user effort by using pairs of instances and their explanations, improving interpretability with minimal input.

Contribution

The paper proposes a novel XBL approach using pairs of instances and GradCAM explanations to lower interaction costs in high-stakes domains.

Findings

Improved explanations (+0.02, +3%) with minimal human input

Reduced classification performance (-0.04, -4%) compared to non-interactive models

Effective in medical image classification tasks

Abstract

eXplanation Based Learning (XBL) is a form of Interactive Machine Learning (IML) that provides a model refining approach via user feedback collected on model explanations. Although the interactivity of XBL promotes model transparency, XBL requires a huge amount of user interaction and can become expensive as feedback is in the form of detailed annotation rather than simple category labelling which is more common in IML. This expense is exacerbated in high stakes domains such as medical image classification. To reduce the effort and expense of XBL we introduce a new approach that uses two input instances and their corresponding Gradient Weighted Class Activation Mapping (GradCAM) model explanations as exemplary explanations to implement XBL. Using a medical image classification task, we demonstrate that, using minimal human input, our approach produces improved explanations (+0.02, +3%) and achieves reduced classification performance (-0.04, -4%) when compared against a model trained without interactions.