paper-with-me

홈 › Papers

Concepts' Information Bottleneck Models

2026-02-16 · Karim Galliamov, Syed M Ahsan Kazmi, Adil Khan, Adín Ramírez Rivera arxiv

Concept Bottleneck Models (CBMs) aim to deliver interpretable predictions by routing decisions through a human-understandable concept layer, yet they often suffer reduced accuracy and concept leakage that undermines faithfulness. We introduce an explicit Information Bottleneck regularizer on the concept layer that penalizes $I(X;C)$ while preserving task-relevant information in $I(C;Y)$, encouraging minimal-sufficient concept representations. We derive two practical variants (a variational objective and an entropy-based surrogate) and integrate them into standard CBM training without architectural changes or additional supervision. Evaluated across six CBM families and three benchmarks, the IB-regularized models consistently outperform their vanilla counterparts. Information-plane analyses further corroborate the intended behavior. These results indicate that enforcing a minimal-sufficient concept bottleneck improves both predictive performance and the reliability of concept-level interventions. The proposed regularizer offers a theoretic-grounded, architecture-agnostic path to more faithful and intervenable CBMs, resolving prior evaluation inconsistencies by aligning training protocols and demonstrating robust gains across model families and datasets.

📄 PDF Abstract BibTeX arXiv:2602.14626

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Learning Concept Bottleneck Models from Mechanistic Explanations

2026-03-07 · Antonio De Santis, Schrasing Tong, Marco Brambilla, Lalana Kagal arxiv

Concept Bottleneck Models (CBMs) aim for ante-hoc interpretability by learning a bottleneck layer that predicts interpretable concepts before the decision. State-of-the-art approaches typically select which concepts to l…

Knowledge Graphs

Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification

2022-11-21 · CVPR 2023 1 · Yue Yang, Artemis Panagopoulou, Shenghao Zhou, Daniel Jin 외

Concept Bottleneck Models (CBM) are inherently interpretable models that factor model decisions into human-readable concepts. They allow people to easily understand why a model is failing, a critical feature for high-sta…

image-classificationImage ClassificationLanguage ModelingLanguage Modelling

Eliminating Information Leakage in Hard Concept Bottleneck Models with Supervised, Hierarchical Concept Learning

2024-02-03 · Ao Sun, Yuanyuan Yuan, Pingchuan Ma, Shuai Wang

Concept Bottleneck Models (CBMs) aim to deliver interpretable and interventionable predictions by bridging features and labels with human-understandable concepts. While recent CBMs show promising potential, they suffer f…

The Decoupling Concept Bottleneck Model

2024-11-01 · IEEE Transactions on Pattern Analysis and Machine Intelligence 2024 11 · Rui Zhang, Xingbo Du, Junchi Yan, Shihua Zhang

The Concept Bottleneck Model (CBM) is an interpretable neural network that leverages high-level concepts to explainmodel decisions and conduct human-machine interaction. However, in real-world scenarios, the deficiency o…

modelMutual Information Estimation

Towards learning to explain with concept bottleneck models: mitigating information leakage

2022-11-07 · Joshua Lockhart, Nicolas Marchesotti, Daniele Magazzeni, Manuela Veloso

Concept bottleneck models perform classification by first predicting which of a list of human provided concepts are true about a datapoint. Then a downstream model uses these predicted concept labels to predict the targe…