Graph Concept Bottleneck Models

TMLR Paper6266 Authors

Abstract: Concept Bottleneck Models (CBMs) have emerged as a prominent framework for interpretable deep learning, providing human-understandable intermediate concepts that enable transparent reasoning and direct intervention. However, existing CBMs typically assume conditional independence among concepts given the label, overlooking the intrinsic dependencies and correlations that often exist among them. In practice, concepts are rarely isolated: modifying one concept may inherently influence others. Ignoring these relationships can lead to oversimplified representations and weaken interpretability. To address this limitation, we introduce **Graph CBMs**, a novel variant of CBMs that explicitly models the relational structure among concepts through a latent concept graph. Our approach can be seamlessly integrated into existing CBMs as a lightweight, plug-and-play module, enriching their reasoning capability without sacrificing interpretability. Experimental results on multiple real-world image classification benchmarks demonstrate that Graph CBMs (1) achieve higher predictive accuracy while revealing meaningful concept structures, (2) enable more effective and robust concept-level interventions, and (3) maintain stable performance across diverse architectures and training setups.

Submission Type: Regular submission (no more than 12 pages of main content)

Assigned Action Editor: ~Samira_Ebrahimi_Kahou1

Submission Number: 6266