Evidential Deep Learning (EDL) is a popular framework for uncertainty-aware classification that models predictive uncertainty via Dirichlet distributions parameterized by neural networks. Despite its popularity, its theoretical foundations and behavior under distributional shift remain poorly understood. In this work, we provide a principled statistical interpretation by proving that EDL training corresponds to amortized variational inference in a hierarchical Bayesian model with a tempered pseudo-likelihood. This perspective reveals a major drawback: standard EDL conflates epistemic and aleatoric uncertainty, leading to systematic overconfidence on out-of-distribution (OOD) inputs. To address this, we introduce Density-Informed Pseudo-count EDL (DIP-EDL), a new parametrization that decouples class prediction from the magnitude of uncertainty by separately estimating the conditional label distribution and the marginal covariate density. This separation preserves evidence in high-density regions while shrinking predictions toward a uniform prior for OOD data. Theoretically, we prove that DIP-EDL achieves asymptotic concentration. Empirically, we show that our method enhances interpretability and improves robustness and uncertainty calibration under distributional shift.
Université de Technologie de Compiègne（贡比涅技术大学）；Shanghai University（上海大学）
Evidential clustering is an approach to clustering in which cluster-membership uncertainty is represented by a collection of Dempster-Shafer mass functions forming an evidential partition. In this paper, we propose to construct these mass functions by bootstrapping finite mixture models. In the first step, we compute bootstrap percentile confidence intervals for all pairwise probabilities (the probabilities for any two objects to belong to the same class). We then construct an evidential partition such that the pairwise belief and plausibility degrees approximate the bounds of the confidence i…
PIETRA: Physics-Informed Evidential Learning for Traversing Out-of-Distribution Terrain
Massachusetts Institute of Technology（麻省理工学院）；Mitsubishi Electric Research Laboratories (MERL)（三菱电机研究实验室）；George Mason University（乔治梅森大学）；DEVCOM Army Research Laboratory（DEVCOM陆军研究实验室）
Deterministic neural networks (NNs) are increasingly being deployed in safety critical domains, where calibrated, robust, and efficient measures of uncertainty are crucial. In this paper, we propose a novel method for training non-Bayesian NNs to estimate a continuous target as well as its associated evidence in order to learn both aleatoric and epistemic uncertainty. We accomplish this by placing evidential priors over the original Gaussian likelihood function and training the NN to infer the hyperparameters of the evidential distribution. We additionally impose priors during training such th…
Evidential time-to-event prediction with calibrated uncertainty quantification
Saw Swee Hock School of Public Health, National University of Singapore（新加坡国立大学苏瑞福公共卫生学院）；Institute of Data Science, National University of Singapore（新加坡国立大学数据科学研究所）；Université de Technologie de Compiègne, CNRS, Heudiasyc（贡比涅技术大学、法国国家科研中心、Heudiasyc实验室）；Institut universitaire de France（法国大学研究院）
University of Southern Denmark（南丹麦大学）；Istanbul Technical University（伊斯坦布尔技术大学）；Heidelberg University（海德堡大学）；Aalto University（阿尔托大学）
A probabilistic classifier with reliable predictive uncertainties i) fits successfully to the target domain data, ii) provides calibrated class probabilities in difficult regions of the target domain (e.g.\ class overlap), and iii) accurately identifies queries coming out of the target domain and rejects them. We introduce an original combination of Evidential Deep Learning, Neural Processes, and Neural Turing Machines capable of providing all three essential properties mentioned above for total uncertainty quantification. We observe our method on five classification tasks to be the only one t…
EvidentialRAG: Quantifying and Mitigating Information Conflict in Multi-Source Retrieval-Augmented Generation via Evidential Deep Learning
School of Computing, Wichita State University（威奇托州立大学计算学院）；Department of Computer Science, American International University-Bangladesh（美国国际孟加拉大学计算机科学系）
Evidential Deep Learning: Enhancing Predictive Uncertainty Estimation for Earth System Science Applications
National Center for Atmospheric Research（国家大气研究中心）；Cooperative Institute for Severe and High-Impact Weather Research and Operations（恶劣与高影响天气研究与合作研究所）；National Severe Storms Laboratory（国家强风暴实验室）；University Corporation for Atmospheric Research（大学大气研究公司）；University of Maryland（马里兰大学）；University at Albany, State University of New York（纽约州立大学奥尔巴尼分校）；Colorado State University（科罗拉多州立大学）；The Pennsylvania State University（宾夕法尼亚州立大学）
Credal and Interval Deep Evidential Classifications
Department of Computer Science, The University of Manchester（曼彻斯特大学计算机科学系）；School of Engineering, Computing and Mathematics, Oxford Brookes University（奥克斯布里奇大学工程、计算与数学学院）
Calibrated and uncertain? Evaluating uncertainty estimates in binary classification models
Department of Computer science, Electrical engineering and Mathematical sciences Western Norway University of Applied Sciences（计算机科学、电气工程和数学科学系西部挪威应用科学大学）；Department of Informatics University of Bergen（信息学院卑尔根大学）
Siemens AG（西门子股份公司）；Technical University of Munich（慕尼黑工业大学）
To facilitate a wide-spread acceptance of AI systems guiding decision making in real-world applications, trustworthiness of deployed models is key. That is, it is crucial for predictive models to be uncertainty-aware and yield well-calibrated (and thus trustworthy) predictions for both in-domain samples as well as under domain shift. Recent efforts to account for predictive uncertainty include post-processing steps for trained neural networks, Bayesian neural networks as well as alternative non-Bayesian approaches such as ensemble approaches and evidential deep learning. Here, we propose an ef…
Current approaches in approximate inference for Bayesian neural networks minimise the Kullback-Leibler divergence to approximate the true posterior over the weights. However, this approximation is without knowledge of the final application, and therefore cannot guarantee optimal predictions for a given task. To make more suitable task-specific approximations, we introduce a new loss-calibrated evidence lower bound for Bayesian neural networks in the context of supervised learning, informed by Bayesian decision theory. By introducing a lower bound that depends on a utility function, we ensure t…
Centre for Artificial Intelligence, University College London（人工智能研究中心，伦敦大学学院）；Heudiasyc Laboratory（Heudiasyc实验室）；Mila - Quebec AI Institute（魁北克人工智能研究所）
Operator-Informed Gaussian Processes for Complex Helmholtz Wavefields: From Synthetic Benchmarks to In Vivo Brain Elastography
Department of Civil and Systems Engineering, Johns Hopkins University（约翰霍普金斯大学土木与系统工程系）；Department of Aerospace Engineering and Mechanics, University of Minnesota（明尼苏达大学航空航天工程与力学系）
Estimated uncertainty by approximate posteriors in Bayesian neural networks are prone to miscalibration, which leads to overconfident predictions in critical tasks that have a clear asymmetric cost or significant losses. Here, we extend the approximate inference for the loss-calibrated Bayesian framework to dropweights based Bayesian neural networks by maximising expected utility over a model posterior to calibrate uncertainty in deep learning. Furthermore, we show that decisions informed by loss-calibrated uncertainty can improve diagnostic performance to a greater extent than straightforward…
