paper-with-me

Papers

Credal Ensemble Distillation for Uncertainty Quantification

2025-11-14 · Kaizheng Wang, Fabio Cuzzolin, David Moens, Hans Hallez arxiv

Deep ensembles (DE) have emerged as a powerful approach for quantifying predictive uncertainty and distinguishing its aleatoric and epistemic components, thereby enhancing model robustness and reliability. However, their high computational and memory costs during inference pose significant challenges for wide practical deployment. To overcome this issue, we propose credal ensemble distillation (CED), a novel framework that compresses a DE into a single model, CREDIT, for classification tasks. Instead of a single softmax probability distribution, CREDIT predicts class-wise probability intervals that define a credal set, a convex set of probability distributions, for uncertainty quantification. Empirical results on out-of-distribution detection benchmarks demonstrate that CED achieves superior or comparable uncertainty estimation compared to several existing baselines, while substantially reducing inference overhead compared to DE.

📄 PDF Abstract BibTeX arXiv:2511.13766

Code (0)

등록된 구현이 없습니다.

Tasks

Out-of-Distribution Detection

Similar Papers 제목 키워드 기반

Ensemble-based Uncertainty Quantification: Bayesian versus Credal Inference

2021-07-21 · Mohammad Hossein Shaker, Eyke Hüllermeier

The idea to distinguish and quantify two important types of uncertainty, often referred to as aleatoric and epistemic, has received increasing attention in machine learning research in the last couple of years. In this p…

Ensemble LearningUncertainty Quantification

Credal Graph Neural Networks

2025-12-02 · Matteo Tolloso, Davide Bacciu arxiv

Uncertainty quantification is essential for deploying reliable Graph Neural Networks (GNNs), where existing approaches primarily rely on Bayesian inference or ensembles. In this paper, we introduce the first credal graph…

Node ClassificationBayesian Inference

Distilling Calibration via Conformalized Credal Inference

2025-01-10 · Jiayi Huang, Sangwoo Park, Nicola Paoletti, Osvaldo Simeone

Deploying artificial intelligence (AI) models on edge devices involves a delicate balance between meeting stringent complexity constraints, such as limited memory and energy resources, and ensuring reliable performance i…

Bayesian InferenceUncertainty Quantification

CreINNs: Credal-Set Interval Neural Networks for Uncertainty Estimation in Classification Tasks

2024-01-10 · Kaizheng Wang, Keivan Shariatmadar, Shireen Kudukkil Manchingal, Fabio Cuzzolin 외

Effective uncertainty estimation is becoming increasingly attractive for enhancing the reliability of neural networks. This work presents a novel approach, termed Credal-Set Interval Neural Networks (CreINNs), for classi…

Binary ClassificationOut-of-Distribution DetectionUncertainty Quantification

Is the Volume of a Credal Set a Good Measure for Epistemic Uncertainty?

2023-06-16 · Yusuf Sale, Michele Caprio, Eyke Hüllermeier

Adequate uncertainty representation and quantification have become imperative in various scientific disciplines, especially in machine learning and artificial intelligence. As an alternative to representing uncertainty v…

Binary ClassificationMulti-class Classification