Evidential deep learning (EDL) has shown remarkable success in uncertainty estimation. However, there is still room for improvement, particularly in out-of-distribution (OOD) detection and classification tasks. The limited OOD detection performance of EDL arises from its inability to reflect the distance between the testing example and training data when quantifying uncertainty, while its limited classification performance stems from its parameterization of the concentration parameters. To address these limitations, we propose a novel method called Density Aware Evidential Deep Learning (DAEDL). DAEDL integrates the feature space density of the testing example with the output of EDL during the prediction stage, while using a novel parameterization that resolves the issues in the conventional parameterization. We prove that DAEDL enjoys a number of favorable theoretical properties. DAEDL demonstrates state-of-the-art performance across diverse downstream tasks related to uncertainty estimation and classification
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…
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…
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）
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…
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…
IT University of Copenhagen（哥本哈根信息技术大学）；Technical University of Denmark（丹麦技术大学）；Pioneer Centre for Artificial Intelligence（先锋人工智能中心）
Popular approaches for quantifying predictive uncertainty in deep neural networks often involve distributions over weights or multiple models, for instance via Markov Chain sampling, ensembling, or Monte Carlo dropout. These techniques usually incur overhead by having to train multiple model instances or do not produce very diverse predictions. This comprehensive and extensive survey aims to familiarize the reader with an alternative class of models based on the concept of Evidential Deep Learning: For unfamiliar data, they aim to admit "what they don't know", and fall back onto a prior belief…
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…
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）
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）
In this paper, we propose TEDL, a two-stage learning approach to quantify uncertainty for deep learning models in classification tasks, inspired by our findings in experimenting with Evidential Deep Learning (EDL) method, a recently proposed uncertainty quantification approach based on the Dempster-Shafer theory. More specifically, we observe that EDL tends to yield inferior AUC compared with models learnt by cross-entropy loss and is highly sensitive in training. Such sensitivity is likely to cause unreliable uncertainty estimation, making it risky for practical applications. To mitigate both…
Equivariant Evidential Deep Learning for Interatomic Potentials
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；College of Computer Science and Artificial Intelligence, Fudan University（复旦大学计算机科学与人工智能学院）；The Chinese University of Hong Kong（香港中文大学）；Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）
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 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）
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）
Uncertainty-Error correlations in Evidential Deep Learning models for biomedical segmentation
Gryphon Center for Artificial Intelligence and Theoretical Sciences, Singapore University of Pennsylvania, Perelman School of Medicine, Department of Radiation Oncology（格雷芬人工智能与理论科学中心，新加坡大学匹兹堡大学，佩尔曼医学学院，放射肿瘤学系）；Georgia Institute of Technology（佐治亚理工学院）；University of Pennsylvania, Perelman School of Medicine, Department of Radiation Oncology（宾夕法尼亚大学，佩尔曼医学学院，放射肿瘤学系）
Robust Adversarial Quantification via Conflict-Aware Evidential Deep Learning
Department of Computer Science, University of York, UK（英国约克大学计算机科学系）；Department of Elect. Eng., and Computer Science and Eng., Cyprus University of Technology, Cyprus（塞浦路斯技术大学电子工程与计算机科学系）
Uncertainty-Supervised Interpretable and Robust Evidential Segmentation
School of Data Science, Fudan University, Shanghai, China（复旦大学数据科学学院）；Institute of Science and Technology for Brain-inspired intelligence, Fudan University, Shanghai, China（复旦大学脑启发式智能技术研究所）；Nuffield Department of Population Health, University of Oxford, Oxford, UK（牛津大学人口健康牛津部门）
DPsurv: Dual-Prototype Evidential Fusion for Uncertainty-Aware and Interpretable Whole-Slide Image Survival Prediction
National University of Singapore；National University of Singapore Guangzhou Research Translation；Innovation Institute；Imperial College London；Peking Union Medical College Hospital, Chinese Academy of Medical Sciences \& Peking Union Medical College；Hunan University；Institute of High Performance Computing, Agency for Science, Technology；Research (A STAR)
Hyper Evidential Deep Learning to Quantify Composite Classification Uncertainty
The University of Texas at Dallas（德克萨斯大学达拉斯分校）；US Army Research Laboratory（美国陆军研究实验室）；University of Oslo（奥斯陆大学）；Virginia Tech（弗吉尼亚理工大学）；University of the District of Columbia（哥伦比亚特区大学）
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）
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）
Variational Inference for Evidential Deep Learning
School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）；School of Computing Information Sciences, Saint Francis University（圣弗朗西斯大学计算信息科学学院）；Department of Computer Science, City University of Hong Kong（香港城市大学计算机科学系）；Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, China（新一代人工智能技术及其交叉应用关键实验室（东南大学），中华人民共和国教育部，中国）
EVORA: Deep Evidential Traversability Learning for Risk-Aware Off-Road Autonomy
Massachusetts Institute of Technology（麻省理工学院）；DEVCOM Army Research Laboratory（DEVCOM陆军研究实验室）；Boston Dynamics AI Institute（波士顿动力人工智能研究所）；Northeastern University（东北大学）
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）
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…
National University of Singapore（新加坡国立大学）；Institute for Infocomm Research, A*STAR（新加坡科技研究局资讯通信研究院）；Singapore University of Technology and Design（新加坡科技设计大学）
Deep learning approaches achieve state-of-the-art performance for classifying radiology images, but rely on large labelled datasets that require resource-intensive annotation by specialists. Both semi-supervised learning and active learning can be utilised to mitigate this annotation burden. However, there is limited work on combining the advantages of semi-supervised and active learning approaches for multi-label medical image classification. Here, we introduce a novel Consistency-based Semi-supervised Evidential Active Learning framework (CSEAL). Specifically, we leverage predictive uncertai…
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）
University of Texas at Dallas（德克萨斯大学达拉斯分校）；NEC Laboratories America（NEC美国实验室）
Sound Event Early Detection (SEED) is an essential task in recognizing the acoustic environments and soundscapes. However, most of the existing methods focus on the offline sound event detection, which suffers from the over-confidence issue of early-stage event detection and usually yield unreliable results. To solve the problem, we propose a novel Polyphonic Evidential Neural Network (PENet) to model the evidential uncertainty of the class probability with Beta distribution. Specifically, we use a Beta distribution to model the distribution of class probabilities, and the evidential uncertain…
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 …
