KL-Guided Concept-Based Learning for Explainable Classification
Overview & Synopsis
Concept Bottleneck Models (CBMs) offer an interpretable framework for deep learning by introducing human-understandable concepts as intermediaries between input data and class predictions. However, the unconstrained learning of concept-to-class mappings often results in unfaithful explanations and shortcut reliance. In this work, we present KL-CBM, a novel CBM architecture that integrates a transparent, probabilistic module with a flexible dense classifier. The transparent head estimates class probabilities based on the alignment between predicted concepts and empirical class-specific profiles. Simultaneously, a dense classifier following the concept layer is softly aligned to the transparent head using Kullback-Leibler (KL) divergence. This encourages predictive consistency with interpretable modeling without sacrificing model capacity. We evaluate KL-CBM on two real-world conceptannotated datasets-AwA2 and aPY-and demonstrate that it achieves strong classification performance and competitive concept prediction accuracy. Our results highlight that KL-CBM maintains semantic alignment between concepts and classes, exhibits robustness to concept-level perturbations, and yields faithful concept-based explanations. Overall, KL-CBM advances the trade-off between interpretability and accuracy, offering a principled and flexible alternative to conventional CBMs.
hal.science)
← / → for pages • + / - for zoom • 0 to fit width
Powered by Mozilla PDF.js v3.11
Document Information
| Document Title | KL-Guided Concept-Based Learning for Explainable Classification |
|---|---|
| Author / Organization | Rim El Cheikh, Issam Falih, Engelbert Mephu Nguifo |
| Subject & Discipline | Multidisciplinary Academic Open Research |
| Categories | Science & Mathematics |
| Publication Year | 2026 |
| License / Rights | Open Access / Creative Commons |
| Resource Verification | Listed PDF (Verification Pending) |
| Original Host Website |
HAL Open Science
(hal.science)
|
| File Format | application/pdf (Portable Document Format) |
| Language | EN |
| Catalog ID | DOC-195242 |
| Original Source Link | Visit Source Page on hal.science » |