Mixture of Concept Bottleneck Experts
This work addresses interpretability and adaptability issues in machine learning for users needing transparent models, though it appears incremental as it builds on existing CBMs.
The paper tackles the limitation of Concept Bottleneck Models (CBMs) in predictive accuracy and adaptability by proposing Mixture of Concept Bottleneck Experts (M-CBEs), which generalizes CBMs with multiple experts and varied functional forms, enabling better navigation of the accuracy-interpretability trade-off.
Concept Bottleneck Models (CBMs) promote interpretability by grounding predictions in human-understandable concepts. However, existing CBMs typically fix their task predictor to a single linear or Boolean expression, limiting both predictive accuracy and adaptability to diverse user needs. We propose Mixture of Concept Bottleneck Experts (M-CBEs), a framework that generalizes existing CBMs along two dimensions: the number of experts and the functional form of each expert, exposing an underexplored region of the design space. We investigate this region by instantiating two novel models: Linear M-CBE, which learns a finite set of linear expressions, and Symbolic M-CBE, which leverages symbolic regression to discover expert functions from data under user-specified operator vocabularies. Empirical evaluation demonstrates that varying the mixture size and functional form provides a robust framework for navigating the accuracy-interpretability trade-off, adapting to different user and task needs.