Evidential Deep Learning (EDL) has emerged as an efficient, sampling-free strategy for uncertainty estimation. A series of EDL variants have been proposed to address specific limitations of the original framework, achieving notable success. However, the underlying theoretical structure of EDL and the relationships among these variants have received limited systematic investigation. In this work, we establish a principled theoretical foundation for EDL by interpreting it within a generalized Bayesian framework that includes prior specification, posterior update, and training objective. We further characterize evidential uncertainty from a Bayesian distributional uncertainty viewpoint, established via asymptotic analysis. Building on this perspective, we further propose Generalized Evidential Deep Learning (GEDL), a unified and extensible framework that explicitly disentangles the roles of individual components and systematically relates GEDL to existing variants. Extensive experiments demonstrate that GEDL yields comparable results on classification, uncertainty estimation and OOD detections, with theoretical grounding.
Heidelberg University（海德堡大学）；Bosch Center for Artificial Intelligence（博世人工智能中心）
We propose a novel method for closed-form predictive distribution modeling with neural nets. In quantifying prediction uncertainty, we build on Evidential Deep Learning, which has been impactful as being both simple to implement and giving closed-form access to predictive uncertainty. We employ it to model aleatoric uncertainty and extend it to account also for epistemic uncertainty by converting it to a Bayesian Neural Net. While extending its uncertainty quantification capabilities, we maintain its analytically accessible predictive distribution model by performing progressive moment matchin…
German Aerospace Center (DLR)（德国航空航天中心）；Institute for Simulation Intelligence（模拟智能研究所）
There is significant need for principled uncertainty reasoning in machine learning systems as they are increasingly deployed in safety-critical domains. A new approach with uncertainty-aware neural networks (NNs), based on learning evidential distributions for aleatoric and epistemic uncertainties, shows promise over traditional deterministic methods and typical Bayesian NNs, yet several important gaps in the theory and implementation of these networks remain. We discuss three issues with a proposed solution to extract aleatoric and epistemic uncertainties from regression-based neural networks…
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…
Deargen Inc.（Deargen 公司）；Deargen USA Inc.（Deargen 美国公司）
The Evidential regression network (ENet) estimates a continuous target and its predictive uncertainty without costly Bayesian model averaging. However, it is possible that the target is inaccurately predicted due to the gradient shrinkage problem of the original loss function of the ENet, the negative log marginal likelihood (NLL) loss. In this paper, the objective is to improve the prediction accuracy of the ENet while maintaining its efficient uncertainty estimation by resolving the gradient shrinkage problem. A multi-task learning (MTL) framework, referred to as MT-ENet, is proposed to acco…
Ozyegin University（奥兹耶金大学）；US Army Research Lab（美国陆军研究实验室）；Bosch Center for Artificial Intelligence（博世人工智能中心）
Deterministic neural nets have been shown to learn effective predictors on a wide range of machine learning problems. However, as the standard approach is to train the network to minimize a prediction loss, the resultant model remains ignorant to its prediction confidence. Orthogonally to Bayesian neural nets that indirectly infer prediction uncertainty through weight uncertainties, we propose explicit modeling of the same using the theory of subjective logic. By placing a Dirichlet distribution on the class probabilities, we treat predictions of a neural net as subjective opinions and learn t…
CalPro: Prior-Aware Evidential--Conformal Prediction with Structure-Aware Guarantees for Protein Structures
Department of Computer Science, Iowa State University, Ames, Iowa, USA；Department of Civil, Construction \& Environmental Engineering, Iowa State University, Ames, Iowa, USA
Evidential Deep Learning for Uncertainty Quantification and Out-of-Distribution Detection in Jet Identification using Deep Neural Networks
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；The Grainger College of Engineering（格兰杰工程学院）；Center for Artificial Intelligence Innovation（人工智能创新中心）；National Center for Supercomputing Applications（国家超级计算应用中心）；Siebel School of Computing and Data Science（西贝尔计算与数据科学学院）
Uncertainty Quantification of Wind Gust Predictions in the Northeast United States: An Evidential Neural Network and Explainable Artificial Intelligence Approach
University of Connecticut（康涅狄格大学）；NSF National Center for Atmospheric Research（NSF国家大气研究中心）
Detecting Misbehaviors of Large Vision-Language Models by Evidential Uncertainty Quantification
State Key Laboratory of Advanced Rail Autonomous Operation（先进轨道交通自主运行国家重点实验室）；Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence（北京交通数据挖掘与具身智能重点实验室）；School of Computer Science and Technology, Beijing Jiaotong University（北京交通大学计算机科学与技术学院）；School of Automation and Intelligence, Beijing Jiaotong University（北京交通大学自动化与智能学院）；Beijing Key Laboratory of Security and Privacy in Intelligent Transportation（北京智能交通安全与隐私重点实验室）
Deep ensembles can be considered as the current state-of-the-art for uncertainty quantification in deep learning. While the approach was originally proposed as a non-Bayesian technique, arguments supporting its Bayesian footing have been put forward as well. We show that deep ensembles can be viewed as an approximate Bayesian method by specifying the corresponding assumptions. Our findings lead to an improved approximation which results in an enlarged epistemic part of the uncertainty. Numerical examples suggest that the improved approximation can lead to more reliable uncertainties. Analytica…
In this contribution, we predict the wellhead protection area (WHPA, target), the shape and extent of which is influenced by the distribution of hydraulic conductivity (K), from a small number of tracing experiments (predictor). Our first objective is to make stochastic predictions of the WHPA within the Bayesian Evidential Learning (BEL) framework, which aims to find a direct relationship between predictor and target using machine learning. This relationship is learned from a small set of training models (400) sampled from the prior distribution of K. The associated 400 pairs of simulated pre…
Comparing competing mathematical models of complex natural processes is a shared goal among many branches of science. The Bayesian probabilistic framework offers a principled way to perform model comparison and extract useful metrics for guiding decisions. However, many interesting models are intractable with standard Bayesian methods, as they lack a closed-form likelihood function or the likelihood is computationally too expensive to evaluate. With this work, we propose a novel method for performing Bayesian model comparison using specialized deep learning architectures. Our method is purely …
The Conditional Neural Process (CNP) family of models offer a promising direction to tackle few-shot problems by achieving better scalability and competitive predictive performance. However, the current CNP models only capture the overall uncertainty for the prediction made on a target data point. They lack a systematic fine-grained quantification on the distinct sources of uncertainty that are essential for model training and decision-making under the few-shot setting. We propose Evidential Conditional Neural Processes (ECNP), which replace the standard Gaussian distribution used by CNP with …
Gryphon Center for Artificial Intelligence and Theoretical Sciences（格里芬人工智能与理论科学中心）；Georgia Institute of Technology（佐治亚理工学院）；University of Pennsylvania（宾夕法尼亚大学）
We present a novel class of Physics-Informed Neural Networks that is formulated based on the principles of Evidential Deep Learning, where the model incorporates uncertainty quantification by learning parameters of a higher-order distribution. The dependent and trainable variables of the PDE residual loss and data-fitting loss terms are recast as functions of the hyperparameters of an evidential prior distribution. Our model is equipped with an information-theoretic regularizer that contains the Kullback-Leibler divergence between two inverse-gamma distributions characterizing predictive uncer…
UT Dallas（德克萨斯大学达拉斯分校）；US Army Research Lab（美国陆军研究实验室）；Virginia Tech（弗吉尼亚理工学院暨州立大学）
Traditional deep neural nets (NNs) have shown the state-of-the-art performance in the task of classification in various applications. However, NNs have not considered any types of uncertainty associated with the class probabilities to minimize risk due to misclassification under uncertainty in real life. Unlike Bayesian neural nets indirectly infering uncertainty through weight uncertainties, evidential neural networks (ENNs) have been recently proposed to support explicit modeling of the uncertainty of class probabilities. It treats predictions of an NN as subjective opinions and learns the f…
Imperial College London（帝国理工学院）；TECNALIA（TECNALIA（西班牙技术中心））；University of the Basque Country (UPV/EHU)（巴斯克大学）；Royal Brompton Hospital（皇家布朗普顿医院）
Despite recent advances in the accuracy of brain tumor segmentation, the results still suffer from low reliability and robustness. Uncertainty estimation is an efficient solution to this problem, as it provides a measure of confidence in the segmentation results. The current uncertainty estimation methods based on quantile regression, Bayesian neural network, ensemble, and Monte Carlo dropout are limited by their high computational cost and inconsistency. In order to overcome these challenges, Evidential Deep Learning (EDL) was developed in recent work but primarily for natural image classific…
The University of Texas at Dallas（德克萨斯大学达拉斯分校）；Virginia Tech（弗吉尼亚理工大学）
Traditional deep neural networks (NNs) have significantly contributed to the state-of-the-art performance in the task of classification under various application domains. However, NNs have not considered inherent uncertainty in data associated with the class probabilities where misclassification under uncertainty may easily introduce high risk in decision making in real-world contexts (e.g., misclassification of objects in roads leads to serious accidents). Unlike Bayesian NN that indirectly infer uncertainty through weight uncertainties, evidential NNs (ENNs) have been recently proposed to ex…
Toward Efficient Uncertainty in LLMs through Evidential Knowledge Distillation
Department of Computer Science and Engineering, Indian Institute of Technology Hyderabad（计算机科学与工程系，印度理工学院海得拉巴分校）；Jagiellonian University, Faculty of Mathematics and Computer Science（雅盖隆大学，数学与计算机科学学院）
A Comprehensive Survey on Evidential Deep Learning and Its Applications
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Peng Cheng Laboratory（鹏城实验室）
Evidential Deep Active Learning for Semi-Supervised Classification
College of Information Engineering, Northwest A&F University（信息工程学院，西北农林科技大学）；Hangzhou Dianzi University（杭州电子科技大学）；Department of Communications Sciences, University of Teramo（通讯科学系，乌尔巴诺-特拉莫大学）
Long-tailed classification poses a challenge due to its heavy imbalance in class probabilities and tail-sensitivity risks with asymmetric misprediction costs. Recent attempts have used re-balancing loss and ensemble methods, but they are largely heuristic and depend heavily on empirical results, lacking theoretical explanation. Furthermore, existing methods overlook the decision loss, which characterizes different costs associated with tailed classes. This paper presents a general and principled framework from a Bayesian-decision-theory perspective, which unifies existing techniques including …
Australian Artificial Intelligence Institute, University of Technology Sydney（悉尼科技大学澳大利亚人工智能研究院）
We present geometric Bayesian active learning by disagreements (GBALD), a framework that performs BALD on its core-set construction interacting with model uncertainty estimation. Technically, GBALD constructs core-set on ellipsoid, not typical sphere, preventing low-representative elements from spherical boundaries. The improvements are twofold: 1) relieve uninformative prior and 2) reduce redundant estimations. Theoretically, geodesic search with ellipsoid can derive tighter lower bound on error and easier to achieve zero error than with sphere. Experiments show that GBALD has slight perturba…
The key distinguishing property of a Bayesian approach is marginalization, rather than using a single setting of weights. Bayesian marginalization can particularly improve the accuracy and calibration of modern deep neural networks, which are typically underspecified by the data, and can represent many compelling but different solutions. We show that deep ensembles provide an effective mechanism for approximate Bayesian marginalization, and propose a related approach that further improves the predictive distribution by marginalizing within basins of attraction, without significant overhead. We…
University of Massachusetts, Amherst（马萨诸塞大学阿默斯特分校）
The deep image prior was recently introduced as a prior for natural images. It represents images as the output of a convolutional network with random inputs. For "inference", gradient descent is performed to adjust network parameters to make the output match observations. This approach yields good performance on a range of image reconstruction tasks. We show that the deep image prior is asymptotically equivalent to a stationary Gaussian process prior in the limit as the number of channels in each layer of the network goes to infinity, and derive the corresponding kernel. This informs a Bayesia…
University of Oxford（牛津大学）；Imperial College London（伦敦帝国理工学院）
We take a Bayesian perspective to illustrate a connection between training speed and the marginal likelihood in linear models. This provides two major insights: first, that a measure of a model's training speed can be used to estimate its marginal likelihood. Second, that this measure, under certain conditions, predicts the relative weighting of models in linear model combinations trained to minimize a regression loss. We verify our results in model selection tasks for linear models and for the infinite-width limit of deep neural networks. We further provide encouraging empirical evidence that…
INRIA, SIERRA Project-Team（法国国家信息与自动化研究所，SIERRA项目组）；D.I., Ecole Normale Superieure（巴黎高等师范学校计算机科学系）；Univ Lyon, UJM-Saint-Etienne, CNRS, IOGS, Laboratoire Hubert Curien UMR 5516（里昂大学，圣艾蒂安让·莫内大学，法国国家科学研究中心，IOGS，于贝尔·居里安实验室）；Université Laval（拉瓦尔大学）
We study the issue of PAC-Bayesian domain adaptation: We want to learn, from a source domain, a majority vote model dedicated to a target one. Our theoretical contribution brings a new perspective by deriving an upper-bound on the target risk where the distributions' divergence---expressed as a ratio---controls the trade-off between a source error measure and the target voters' disagreement. Our bound suggests that one has to focus on regions where the source data is informative.From this result, we derive a PAC-Bayesian generalization bound, and specialize it to linear classifiers. Then, we i…
University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；Koc University（科奇大学）
We introduce a Bayesian perspective for the structured matrix factorization problem. The proposed framework provides a probabilistic interpretation for existing geometric methods based on determinant minimization. We model input data vectors as linear transformations of latent vectors drawn from a distribution uniform over a particular domain reflecting structural assumptions, such as the probability simplex in Nonnegative Matrix Factorization and polytopes in Polytopic Matrix Factorization. We represent the rows of the linear transformation matrix as vectors generated independently from a nor…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of California, Berkeley（加州大学伯克利分校）；Rice University（莱斯大学）
Bayesian coresets have emerged as a promising approach for implementing scalable Bayesian inference. The Bayesian coreset problem involves selecting a (weighted) subset of the data samples, such that the posterior inference using the selected subset closely approximates the posterior inference using the full dataset. This manuscript revisits Bayesian coresets through the lens of sparsity constrained optimization. Leveraging recent advances in accelerated optimization methods, we propose and analyze a novel algorithm for coreset selection. We provide explicit convergence rate guarantees and pre…
PRESCRIBE: Predicting Single-Cell Responses with Bayesian Estimation
Shanghai Jiao Tong University（上海交通大学）；Westlake University（西湖大学）；AIMS Lab, The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）AIMS实验室）；The Hong Kong University of Science and Technology（香港科技大学）
Chicago Booth School of Business（芝加哥大学布斯商学院）；University of Chicago（芝加哥大学）；George Mason University（乔治梅森大学）
Deep learning is a form of machine learning for nonlinear high dimensional pattern matching and prediction. By taking a Bayesian probabilistic perspective, we provide a number of insights into more efficient algorithms for optimisation and hyper-parameter tuning. Traditional high-dimensional data reduction techniques, such as principal component analysis (PCA), partial least squares (PLS), reduced rank regression (RRR), projection pursuit regression (PPR) are all shown to be shallow learners. Their deep learning counterparts exploit multiple deep layers of data reduction which provide predicti…
The lottery ticket hypothesis (LTH) has attracted attention because it can explain why over-parameterized models often show high generalization ability. It is known that when we use iterative magnitude pruning (IMP), which is an algorithm to find sparse networks with high generalization ability that can be trained from the initial weights independently, called winning tickets, the initial large learning rate does not work well in deep neural networks such as ResNet. However, since the initial large learning rate generally helps the optimizer to converge to flatter minima, we hypothesize that t…
Mines ParisTech – PSL（巴黎高等矿业学院——巴黎文理研究大学）；Inria（法国国家信息与自动化研究所）；Sorbonne Université（索邦大学）；University College London（伦敦大学学院）
Many practical machine learning tasks can be framed as Structured prediction problems, where several output variables are predicted and considered interdependent. Recent theoretical advances in structured prediction have focused on obtaining fast rates convergence guarantees, especially in the Implicit Loss Embedding (ILE) framework. PAC-Bayes has gained interest recently for its capacity of producing tight risk bounds for predictor distributions. This work proposes a novel PAC-Bayes perspective on the ILE Structured prediction framework. We present two generalization bounds, on the risk and e…
