paper-with-me

홈 › Papers

Process-Guided Concept Bottleneck Model

2026-01-15 · Reza M. Asiyabi, SEOSAW Partnership, Steven Hancock, Casey Ryan arxiv

Concept Bottleneck Models (CBMs) improve the explainability of black-box Deep Learning (DL) by introducing intermediate semantic concepts. However, standard CBMs often overlook domain-specific relationships and causal mechanisms, and their dependence on complete concept labels limits applicability in scientific domains where supervision is sparse but processes are well defined. To address this, we propose the Process-Guided Concept Bottleneck Model (PG-CBM), an extension of CBMs which constrains learning to follow domain-defined causal mechanisms through biophysically meaningful intermediate concepts. Using above ground biomass density estimation from Earth Observation data as a case study, we show that PG-CBM reduces error and bias compared to multiple benchmarks, whilst leveraging multi-source heterogeneous training data and producing interpretable intermediate outputs. Beyond improved accuracy, PG-CBM enhances transparency, enables detection of spurious learning, and provides scientific insights, representing a step toward more trustworthy AI systems in scientific applications.

📄 PDF Abstract BibTeX arXiv:2601.10562

Code (0)

등록된 구현이 없습니다.

Tasks

Density Estimation

Similar Papers 제목 키워드 기반

Concepts Worth Having: Refining VLM-Guided Concept Bottleneck Models with Minimal Annotations

2026-05-13 · Nicola Debole, Andrea Passerini, Stefano Teso, Andrea Pugnana 외 arxiv

Concept-bottleneck models (CBMs) are neural classifiers that compute predictions from high-level concepts extracted from the input. CBMs ensure stakeholders can understand the concepts -- and the predictions they entail …

Active Learning

Language Guided Concept Bottleneck Models for Interpretable Continual Learning

2025-03-30 · CVPR 2025 1 · Lu Yu, Haoyu Han, Zhe Tao, Hantao Yao 외

Continual learning (CL) aims to enable learning systems to acquire new knowledge constantly without forgetting previously learned information. CL faces the challenge of mitigating catastrophic forgetting while maintainin…

Continual LearningDecision Making

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

Exploring Concept Subspace for Self-explainable Text-Attributed Graph Learning

2026-04-13 · Xiaoxue Han, Libo Zhang, Zining Zhu, Yue Ning arxiv

We introduce Graph Concept Bottleneck (GCB) as a new paradigm for self-explainable text-attributed graph learning. GCB maps graphs into a subspace, concept bottleneck, where each concept is a meaningful phrase, and predi…

Graph Learning

Radiologist-Guided Causal Concept Bottleneck Models for Chest X-Ray Interpretation

2026-05-08 · Amy Rafferty, Rishi Ramaesh, Ajitha Rajan arxiv

Concept Bottleneck Models (CBMs) in medical imaging aim to improve model interpretability by predicting intermediate clinical concepts before final diagnoses. However, most existing CBMs treat concepts as discriminative …

Bayesian Inference