Learning from Exemplary Explanations
This addresses the expense of detailed feedback in high-stakes domains like medical image classification, though it is incremental as it builds on existing XBL and GradCAM techniques.
The paper tackled the high cost of user feedback in Explanation Based Learning (XBL) by introducing a method that uses exemplary explanations from two input instances and GradCAM to reduce human input, resulting in improved explanations (+0.02, +3%) but reduced classification performance (-0.04, -4%) compared to a non-interactive model.
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.