Probabilistic Concept Bottleneck Models

2023/06/02 by Eunji Kim, Dahuin Jung, Kim, Eunji +7 · 14 citations
Computer Science · #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning in Healthcare

paper · pdf · doi:10.48550/arxiv.2306.01574

openalex publication_date 2023/06/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/31

Abstract

Interpretable models are designed to make decisions in a human-interpretable manner. Representatively, Concept Bottleneck Models (CBM) follow a two-step process of concept prediction and class prediction based on the predicted concepts. CBM provides explanations with high-level concepts derived from concept predictions; thus, reliable concept predictions are important for trustworthiness. In this study, we address the ambiguity issue that can harm reliability. While the existence of a concept can often be ambiguous in the data, CBM predicts concepts deterministically without considering this ambiguity. To provide a reliable interpretation against this ambiguity, we propose Probabilistic Concept Bottleneck Models (ProbCBM). By leveraging probabilistic concept embeddings, ProbCBM models uncertainty in concept prediction and provides explanations based on the concept and its corresponding uncertainty. This uncertainty enhances the reliability of the explanations. Furthermore, as class uncertainty is derived from concept uncertainty in ProbCBM, we can explain class uncertainty by means of concept uncertainty. Code is publicly available at https://github.com/ejkim47/prob-cbm.

Cited by

• A Tool Bottleneck Framework for Clinically-Informed and Interpretable Medical Image Understanding
• LogicCBMs: Logic-Enhanced Concept-Based Learning
• A Geometric Unification of Concept Learning with Concept Cones
• Exploring the Rashomon Set for Concept-Based Models
• Structurally Separated Uncertainty in Supervised Latent Variable Models
• From Black-box to Causal-box: Towards Building More Interpretable Models
• Uncertainty-Aware Concept Bottleneck Models with Enhanced Interpretability
• Understanding and Improving Adversarial Robustness of Neural Probabilistic Circuits
• xAI-CV: An Overview of Explainable Artificial Intelligence in Computer Vision
• Chat-CBM: Towards Interactive Concept Bottleneck Models with Frozen Large Language Models
• Locality-aware Concept Bottleneck Model
• Graph Concept Bottleneck Models
• Uncertainty-Aware Information Pursuit for Interpretable and Reliable Medical Image Analysis
• MVP-CBM:Multi-layer Visual Preference-enhanced Concept Bottleneck Model for Explainable Medical Image Classification

Related

• Learn to explain yourself, when you can: Equipping Concept Bottleneck Models with the ability to abstain on their concept predictions
• Uncertainty-Aware Concept Bottleneck Models with Enhanced Interpretability
• Stochastic Concept Bottleneck Models
• Estimation of Concept Explanations Should be Uncertainty Aware
• On the Concept Trustworthiness in Concept Bottleneck Models