paper-with-me

Papers

Probabilistic Concept Bottleneck Models

2023-06-02 · Eunji Kim, Dahuin Jung, Sangha Park, Siwon Kim, Sungroh Yoon

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.

📄 PDF Abstract BibTeX arXiv:2306.01574

Code (2)

ejkim47/prob-cbm 공식 구현 pytorch
samuelebortolotti/bears pytorch

Tasks

Prediction

Similar Papers 제목 키워드 기반

EQ-CBM: A Probabilistic Concept Bottleneck with Energy-based Models and Quantized Vectors

2024-09-22 · Sangwon Kim, Dasom Ahn, Byoung Chul Ko, In-Su Jang 외

The demand for reliable AI systems has intensified the need for interpretable deep neural networks. Concept bottleneck models (CBMs) have gained attention as an effective approach by leveraging human-understandable conce…

Concept Flow Models: Anchoring Concept-Based Reasoning with Hierarchical Bottlenecks

2026-06-17 · Ya Wang, Adrian Paschke arxiv

Concept Bottleneck Models (CBMs) enhance interpretability by projecting learned features into a human-understandable concept space. Recent approaches leverage vision-language models to generate concept embeddings, reduci…

Understanding and Improving Adversarial Robustness of Neural Probabilistic Circuits

2025-09-24 · Weixin Chen, Han Zhao arxiv

Neural Probabilistic Circuits (NPCs), a new class of concept bottleneck models, comprise an attribute recognition model and a probabilistic circuit for reasoning. By integrating the outputs from these two modules, NPCs p…

Adversarial RobustnessImage Classification

Energy-Based Concept Bottleneck Models: Unifying Prediction, Concept Intervention, and Probabilistic Interpretations

2024-01-25 · Xinyue Xu, Yi Qin, Lu Mi, Hao Wang 외

Existing methods, such as concept bottleneck models (CBMs), have been successful in providing concept-based interpretations for black-box deep learning models. They typically work by predicting concepts given the input a…

FI-CBL: A Probabilistic Method for Concept-Based Learning with Expert Rules

2024-06-28 · Lev V. Utkin, Andrei V. Konstantinov, Stanislav R. Kirpichenko

A method for solving concept-based learning (CBL) problem is proposed. The main idea behind the method is to divide each concept-annotated image into patches, to transform the patches into embeddings by using an autoenco…