Hierarchical, Interpretable, Label-Free Concept Bottleneck Model
This addresses the problem of interpretability in deep learning for researchers and practitioners by offering a more human-like hierarchical approach, though it is incremental as it builds upon existing CBMs.
The paper tackles the limitation of Concept Bottleneck Models (CBMs) operating at a single semantic level by proposing HIL-CBM, a hierarchical framework that enhances interpretability by mirroring human cognition across multiple abstraction levels, resulting in improved classification accuracy over state-of-the-art sparse CBMs and more interpretable explanations in human evaluations.
Concept Bottleneck Models (CBMs) introduce interpretability to black-box deep learning models by predicting labels through human-understandable concepts. However, unlike humans, who identify objects at different levels of abstraction using both general and specific features, existing CBMs operate at a single semantic level in both concept and label space. We propose HIL-CBM, a Hierarchical Interpretable Label-Free Concept Bottleneck Model that extends CBMs into a hierarchical framework to enhance interpretability by more closely mirroring the human cognitive process. HIL-CBM enables classification and explanation across multiple semantic levels without requiring relational concept annotations. HIL-CBM aligns the abstraction level of concept-based explanations with that of model predictions, progressing from abstract to concrete. This is achieved by (i) introducing a gradient-based visual consistency loss that encourages abstraction layers to focus on similar spatial regions, and (ii) training dual classification heads, each operating on feature concepts at different abstraction levels. Experiments on benchmark datasets demonstrate that HIL-CBM outperforms state-of-the-art sparse CBMs in classification accuracy. Human evaluations further show that HIL-CBM provides more interpretable and accurate explanations, while maintaining a hierarchical and label-free approach to feature concepts.