Controllable Concept Bottleneck Models

TL;DR

Controllable Concept Bottleneck Models (CCBMs) enable efficient, flexible editing of concept-based models through influence function approximations, supporting dynamic updates like data removal, addition, and concept correction without retraining.

Contribution

This paper introduces CCBMs, a novel framework allowing multi-granularity model editing in concept bottleneck models via influence functions, addressing real-world needs for adaptable and maintainable models.

Findings

CCBMs support concept, label, and data-level editing.

Closed-form influence function approximations enable efficient updates.

Experimental results confirm the practicality and adaptability of CCBMs.

Abstract

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.