Uncertainty quantification of machine learning and deep learning methods plays an important role in enhancing trust to the obtained result. In recent years, a numerous number of uncertainty quantification methods have been introduced. Monte Carlo dropout (MC-Dropout) is one of the most well-known techniques to quantify uncertainty in deep learning methods. In this study, we propose two new loss functions by combining cross entropy with Expected Calibration Error (ECE) and Predictive Entropy (PE). The obtained results clearly show that the new proposed loss functions lead to having a calibrated MC-Dropout method. Our results confirmed the great impact of the new hybrid loss functions for minimising the overlap between the distributions of uncertainty estimates for correct and incorrect predictions without sacrificing the model's overall performance.
Cornell University（康奈尔大学）；Cornell Tech（康奈尔理工学院）；Shutterstock（Shutterstock公司）；Rochester Institute of Technology（罗切斯特理工学院）
For many applications it is critical to know the uncertainty of a neural network's predictions. While a variety of neural network parameter estimation methods have been proposed for uncertainty estimation, they have not been rigorously compared across uncertainty measures. We assess four of these parameter estimation methods to calibrate uncertainty estimation using four different uncertainty measures: entropy, mutual information, aleatoric uncertainty and epistemic uncertainty. We evaluate the calibration of these parameter estimation methods using expected calibration error. Additionally, we…
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…
Technical University of Munich（慕尼黑工业大学）；OpenMined；Imperial College London（帝国理工学院）
We show that differentially private stochastic gradient descent (DP-SGD) can yield poorly calibrated, overconfident deep learning models. This represents a serious issue for safety-critical applications, e.g. in medical diagnosis. We highlight and exploit parallels between stochastic gradient Langevin dynamics, a scalable Bayesian inference technique for training deep neural networks, and DP-SGD, in order to train differentially private, Bayesian neural networks with minor adjustments to the original (DP-SGD) algorithm. Our approach provides considerably more reliable uncertainty estimates tha…
Montreal Robotics and Embodied AI Lab（蒙特利尔机器人与具身人工智能实验室）；Mila（米拉人工智能研究所）；Université de Montréal（蒙特利尔大学）；Denso（电装公司）
While modern deep neural networks are performant perception modules, performance (accuracy) alone is insufficient, particularly for safety-critical robotic applications such as self-driving vehicles. Robot autonomy stacks also require these otherwise blackbox models to produce reliable and calibrated measures of confidence on their predictions. Existing approaches estimate uncertainty from these neural network perception stacks by modifying network architectures, inference procedure, or loss functions. However, in general, these methods lack calibration, meaning that the predictive uncertainti…
From the statistical learning perspective, complexity control via explicit regularization is a necessity for improving the generalization of over-parameterized models. However, the impressive generalization performance of neural networks with only implicit regularization may be at odds with this conventional wisdom. In this work, we revisit the importance of explicit regularization for obtaining well-calibrated predictive uncertainty. Specifically, we introduce a probabilistic measure of calibration performance, which is lower bounded by the log-likelihood. We then explore explicit regularizat…
Institute of Mechatronic Systems（机电系统研究所）；Leibniz University Hannover（汉诺威莱布尼茨大学）
Model uncertainty obtained by variational Bayesian inference with Monte Carlo dropout is prone to miscalibration. The uncertainty does not represent the model error well. In this paper, temperature scaling is extended to dropout variational inference to calibrate model uncertainty. Expected uncertainty calibration error (UCE) is presented as a metric to measure miscalibration of uncertainty. The effectiveness of this approach is evaluated on CIFAR-10/100 for recent CNN architectures. Experimental results show, that temperature scaling considerably reduces miscalibration by means of UCE and ena…
Learning atomic forces from uncertainty-calibrated adversarial attacks
Hylleraas Centre for Quantum Molecular Sciences（海利拉斯量子分子科学中心）；Department of Chemistry, University of Oslo（奥斯陆大学化学系）；The Njord Centre, Department of Physics, University of Oslo（尼尔德中心，奥斯陆大学物理系）
Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室）；Arizona State University（亚利桑那州立大学）；IBM Research AI（IBM研究院人工智能部门）
With rapid adoption of deep learning in critical applications, the question of when and how much to trust these models often arises, which drives the need to quantify the inherent uncertainties. While identifying all sources that account for the stochasticity of models is challenging, it is common to augment predictions with confidence intervals to convey the expected variations in a model's behavior. We require prediction intervals to be well-calibrated, reflect the true uncertainties, and to be sharp. However, existing techniques for obtaining prediction intervals are known to produce unsati…
McGill University（麦吉尔大学）；University of Michigan（密歇根大学）
While the accuracy of modern deep learning models has significantly improved in recent years, the ability of these models to generate uncertainty estimates has not progressed to the same degree. Uncertainty methods are designed to provide an estimate of class probabilities when predicting class assignment. While there are a number of proposed methods for estimating uncertainty, they all suffer from a lack of calibration: predicted probabilities can be off from empirical ones by a few percent or more. By restricting the scope of our predictions to only the probability of Top-1 error, we can dec…
We show that a GPT-3 model can learn to express uncertainty about its own answers in natural language -- without use of model logits. When given a question, the model generates both an answer and a level of confidence (e.g. "90% confidence" or "high confidence"). These levels map to probabilities that are well calibrated. The model also remains moderately calibrated under distribution shift, and is sensitive to uncertainty in its own answers, rather than imitating human examples. To our knowledge, this is the first time a model has been shown to express calibrated uncertainty about its own ans…
Manipal Institute of Technology（马尼帕尔理工学院）；Manipal Academy of Higher Education（马尼帕尔高等教育学院）
Deep Ensemble Convolutional Neural Networks has become a methodology of choice for analyzing medical images with a diagnostic performance comparable to a physician, including the diagnosis of Diabetic Retinopathy. However, commonly used techniques are deterministic and are therefore unable to provide any estimate of predictive uncertainty. Quantifying model uncertainty is crucial for reducing the risk of misdiagnosis. A reliable architecture should be well-calibrated to avoid over-confident predictions. To address this, we propose a UATTA-ENS: Uncertainty-Aware Test-Time Augmented Ensemble Tec…
Accurate quantification of uncertainty is crucial for real-world applications of machine learning. However, modern deep neural networks still produce unreliable predictive uncertainty, often yielding over-confident predictions. In this paper, we are concerned with getting well-calibrated predictions in regression tasks. We propose the calibrated regression method using the maximum mean discrepancy by minimizing the kernel embedding measure. Theoretically, the calibration error of our method asymptotically converges to zero when the sample size is large enough. Experiments on non-trivial real d…
Among the many ways of quantifying uncertainty in a regression setting, specifying the full quantile function is attractive, as quantiles are amenable to interpretation and evaluation. A model that predicts the true conditional quantiles for each input, at all quantile levels, presents a correct and efficient representation of the underlying uncertainty. To achieve this, many current quantile-based methods focus on optimizing the so-called pinball loss. However, this loss restricts the scope of applicable regression models, limits the ability to target many desirable properties (e.g. calibrati…
In this paper, we propose a confidence-calibration method for predicting the winner of a famous multiplayer online battle arena (MOBA) game, League of Legends. In MOBA games, the dataset may contain a large amount of input-dependent noise; not all of such noise is observable. Hence, it is desirable to attempt a confidence-calibrated prediction. Unfortunately, most existing confidence calibration methods are pertaining to image and document classification tasks where consideration on uncertainty is not crucial. In this paper, we propose a novel calibration method that takes data uncertainty int…
Towards Intrinsically Calibrated Uncertainty Quantification in Industrial Data-Driven Models via Diffusion Sampler
College of Control Science and Engineering, Zhejiang University（浙江大学控制科学与工程学院）；Electrical Engineering Department, Polytechnique Montreal（蒙特利尔理工学院电气工程系）；GERAD；State Key Lab of General AI, School of Intelligence Science and Technology, Peking University（北京大学智能科学与技术学院通用人工智能国家重点实验室）；Guangdong Provincial Key Laboratory of Petrochemical Equipment Fault Diagnosis, Guangdong University of Petrochemical Technology（广东石油化工学院广东省石化装备故障诊断重点实验室）
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）
Assessing uncertainty is an important step towards ensuring the safety and reliability of machine learning systems. Existing uncertainty estimation techniques may fail when their modeling assumptions are not met, e.g. when the data distribution differs from the one seen at training time. Here, we propose techniques that assess a classification algorithm's uncertainty via calibrated probabilities (i.e. probabilities that match empirical outcome frequencies in the long run) and which are guaranteed to be reliable (i.e. accurate and calibrated) on out-of-distribution input, including input genera…
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）
CLEAR: Calibrated Learning for Epistemic and Aleatoric Risk
Department of Operations, HEC, University of Lausanne（洛桑大学运营管理系）；Department of Statistics, University of California, Berkeley（加州大学伯克利分校统计系）；Department of Electrical Engineering and Computer Science, University of California, Berkeley（加州大学伯克利分校电气工程与计算机科学系）；BegooAI
Obtaining reliable and accurate quantification of uncertainty estimates from deep neural networks is important in safety-critical applications. A well-calibrated model should be accurate when it is certain about its prediction and indicate high uncertainty when it is likely to be inaccurate. Uncertainty calibration is a challenging problem as there is no ground truth available for uncertainty estimates. We propose an optimization method that leverages the relationship between accuracy and uncertainty as an anchor for uncertainty calibration. We introduce a differentiable accuracy versus uncert…
Imputation-free transformer learning enables robust Alzheimer's disease prediction and calibrated uncertainty quantification across heterogeneous clinical cohorts
Platform of Bioinformatics（生物信息平台）；Lausanne University Hospital（洛桑大学医院）；Faculty of Biology and Medicine（生物学与医学学院）；University of Lausanne（洛桑大学）；Leenaards Memory Centre（Leenaards记忆中心）；Department of Clinical Neurosciences（临床神经科学系）
Uncertainty-Calibrated Test-Time Model Adaptation without Forgetting
School of Software Engineering, South China University of Technology（华南理工大学软件工程学院）；Key Laboratory of Big Data and Intelligent Robot, Ministry of Education（教育部大数据与智能机器人重点实验室）；Pazhou Laboratory（琶洲实验室）；Nanyang Technological University（南洋理工大学）；ByteDance, China（字节跳动（中国））；Tencent AI Lab（腾讯AI实验室）；School of Computing, National University of Singapore（新加坡国立大学计算机学院）
Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室）
The role of uncertainty quantification (UQ) in deep learning has become crucial with growing use of predictive models in high-risk applications. Though a large class of methods exists for measuring deep uncertainties, in practice, the resulting estimates are found to be poorly calibrated, thus making it challenging to translate them into actionable insights. A common workaround is to utilize a separate recalibration step, which adjusts the estimates to compensate for the miscalibration. Instead, we propose to repurpose the heteroscedastic regression objective as a surrogate for calibration and…
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）
West Virginia University（西弗吉尼亚大学）；Virginia Tech（弗吉尼亚理工学院暨州立大学）；Space Environments Technologies（空间环境技术公司）
The Mass Spectrometer and Incoherent Scatter radar (MSIS) model family has been developed and improved since the early 1970's. The most recent version of MSIS is the Naval Research Laboratory (NRL) MSIS 2.0 empirical atmospheric model. NRLMSIS 2.0 provides species density, mass density, and temperature estimates as function of location and space weather conditions. MSIS models have long been a popular choice of atmosphere model in the research and operations community alike, but - like many models - does not provide uncertainty estimates. In this work, we develop an exospheric temperature mode…
For responsible decision making in safety-critical settings, machine learning models must effectively detect and process edge-case data. Although existing works show that predictive uncertainty is useful for these tasks, it is not evident from literature which uncertainty-aware models are best suited for a given dataset. Thus, we compare six uncertainty-aware deep learning models on a set of edge-case tasks: robustness to adversarial attacks as well as out-of-distribution and adversarial detection. We find that the geometry of the data sub-manifold is an important factor in determining the suc…
Uncertainty-Aware Calibrated Clinical Text Classification with Large Language Models
Faculty of Dental Medicine and Oral Health Sciences, McGill University（牙医学院与口腔健康科学学院，麦吉尔大学）；McGill University（麦吉尔大学）；Mila–Quebec Artificial Intelligence Institute（魁北克人工智能研究所）；School of Computer Science, McGill University（计算机科学学院，麦吉尔大学）
ISCTE – Instituto Universitário de Lisboa（里斯本大学学院）；PDMFC；IT – Instituto de Telecomunicações（电信研究所）；FCT – Universidade Nova de Lisboa（新里斯本大学科学与技术学院）；CTTC - Centre Tecnològic de Telecomunicacions de Catalunya（加泰罗尼亚电信技术中心）
Only increasing accuracy without considering uncertainty may negatively impact Deep Neural Network (DNN) decision-making and decrease its reliability. This paper proposes five combined preprocessing and post-processing methods for time-series binary classification problems that simultaneously increase the accuracy and reliability of DNN outputs applied in a 5G UAV security dataset. These techniques use DNN outputs as input parameters and process them in different ways. Two methods use a well-known Machine Learning (ML) algorithm as a complement, and the other three use only confidence values t…
Algorithms with Calibrated Machine Learning Predictions
Department of Management Science \& Engineering, Stanford University, Stanford, CA, USA；Department of Computer Science, Stanford University, Stanford, CA, USA
Probabilistic predictions from neural networks which account for predictive uncertainty during classification is crucial in many real-world and high-impact decision making settings. However, in practice most datasets are trained on non-probabilistic neural networks which by default do not capture this inherent uncertainty. This well-known problem has led to the development of post-hoc calibration procedures, such as Platt scaling (logistic), isotonic and beta calibration, which transforms the scores into well calibrated empirical probabilities. A plausible alternative to the calibration approa…
Technical University of Denmark（丹麦技术大学）；Rigshospitalet, Copenhagen University Hospital（哥本哈根大学医院 Rigshospitalet）；University of Copenhagen（哥本哈根大学）
Data-driven methods based on machine learning have the potential to accelerate computational analysis of atomic structures. In this context, reliable uncertainty estimates are important for assessing confidence in predictions and enabling decision making. However, machine learning models can produce badly calibrated uncertainty estimates and it is therefore crucial to detect and handle uncertainty carefully. In this work we extend a message passing neural network designed specifically for predicting properties of molecules and materials with a calibrated probabilistic predictive distribution. …
Methods for reasoning under uncertainty are a key building block of accurate and reliable machine learning systems. Bayesian methods provide a general framework to quantify uncertainty. However, because of model misspecification and the use of approximate inference, Bayesian uncertainty estimates are often inaccurate -- for example, a 90% credible interval may not contain the true outcome 90% of the time. Here, we propose a simple procedure for calibrating any regression algorithm; when applied to Bayesian and probabilistic models, it is guaranteed to produce calibrated uncertainty estimates g…
