This part looks alike this: identifying important parts of explained instances and prototypes
This work addresses the interpretability gap in prototype-based explanations for machine learning users, though it appears incremental as it builds on existing prototype selection methods.
The paper tackles the problem of prototype-based explanations failing to highlight the most relevant features by proposing a method to identify 'alike parts' using feature importance scores, which improves user comprehension while maintaining or increasing predictive accuracy on six benchmark datasets.
Although prototype-based explanations provide a human-understandable way of representing model predictions they often fail to direct user attention to the most relevant features. We propose a novel approach to identify the most informative features within prototypes, termed alike parts. Using feature importance scores derived from an agnostic explanation method, it emphasizes the most relevant overlapping features between an instance and its nearest prototype. Furthermore, the feature importance score is incorporated into the objective function of the prototype selection algorithms to promote global prototypes diversity. Through experiments on six benchmark datasets, we demonstrate that the proposed approach improves user comprehension while maintaining or even increasing predictive accuracy.