Controllable Concept Bottleneck Models
This addresses the need for dynamic and trustworthy CBMs in applications requiring continuous maintenance like unlearning or incremental learning, though it is incremental as it builds on existing CBM frameworks.
The paper tackles the challenge of efficiently editing Concept Bottleneck Models (CBMs) for real-world deployment without retraining, proposing Controllable CBMs (CCBMs) that support concept-label, concept, and data-level edits using closed-form approximations, achieving practical efficiency and adaptability in experiments.
Concept Bottleneck Models (CBMs) have garnered much attention for their ability to elucidate the prediction process through a human-understandable concept layer. However, most previous studies focused on static scenarios where the data and concepts are assumed to be fixed and clean. In real-world applications, deployed models require continuous maintenance: we often need to remove erroneous or sensitive data (unlearning), correct mislabeled concepts, or incorporate newly acquired samples (incremental learning) to adapt to evolving environments. Thus, deriving efficient editable CBMs without retraining from scratch remains a significant challenge, particularly in large-scale applications. To address these challenges, we propose Controllable Concept Bottleneck Models (CCBMs). Specifically, CCBMs support three granularities of model editing: concept-label-level, concept-level, and data-level, the latter of which encompasses both data removal and data addition. CCBMs enjoy mathematically rigorous closed-form approximations derived from influence functions that obviate the need for retraining. Experimental results demonstrate the efficiency and adaptability of our CCBMs, affirming their practical value in enabling dynamic and trustworthy CBMs.