Personalized Interpretability -- Interactive Alignment of Prototypical Parts Networks
This addresses the issue of making AI explanations more comprehensible and aligned with user preferences for users of interpretable machine learning systems, though it is incremental as it builds on existing concept-based methods.
The paper tackled the problem of concept inconsistency in interpretable neural networks, where visual features are inappropriately mixed, by introducing YoursProtoP, an interactive strategy that personalizes prototypical parts based on user feedback, achieving concept consistency without compromising model accuracy.
Concept-based interpretable neural networks have gained significant attention due to their intuitive and easy-to-understand explanations based on case-based reasoning, such as "this bird looks like those sparrows". However, a major limitation is that these explanations may not always be comprehensible to users due to concept inconsistency, where multiple visual features are inappropriately mixed (e.g., a bird's head and wings treated as a single concept). This inconsistency breaks the alignment between model reasoning and human understanding. Furthermore, users have specific preferences for how concepts should look, yet current approaches provide no mechanism for incorporating their feedback. To address these issues, we introduce YoursProtoP, a novel interactive strategy that enables the personalization of prototypical parts - the visual concepts used by the model - according to user needs. By incorporating user supervision, YoursProtoP adapts and splits concepts used for both prediction and explanation to better match the user's preferences and understanding. Through experiments on both the synthetic FunnyBirds dataset and a real-world scenario using the CUB, CARS, and PETS datasets in a comprehensive user study, we demonstrate the effectiveness of YoursProtoP in achieving concept consistency without compromising the accuracy of the model.