Proposes a method to quantify uncertainty in graph neural networks for node classification.
problem Uncertainty in graph neural networks for node classification.
method Bayesian uncertainty propagation (BUP) method embedding GNNs in a Bayesian framework.
result Demonstrates superior performance of the proposed method on benchmark datasets.
The volume of a credal set correlates with epistemic uncertainty in binary classification but not in multi-class.
problem Representing and quantifying epistemic uncertainty in machine learning.
method Examined the geometric representation of credal sets as d-dimensional polytopes and their volume as a measure of uncertainty. result The volume of a credal set is a meaningful measure of epistemic uncertainty in binary classification but not in multi-class.
Study benchmarks uncertainty quantification in chest X-ray classification.
problem Reliable uncertainty quantification for medical AI models.
method Evaluation of 13 uncertainty quantification methods on MIMIC-CXR-JPG dataset.
result Insights into effectiveness and disentanglement of epistemic and aleatoric uncertainties.
Bayesian framework improves ML classification models' uncertainty estimates.
problem Ensuring trustworthy AI predictions with explicit uncertainty quantification.
method Proposes a Bayesian framework for generative ML classification models that accounts for input measurement uncertainty.
result The BQDA model outperforms other models in terms of interpretability, explicit uncertainty modeling, and computational efficiency.
Graph Posterior Network improves uncertainty estimation for node classification in interdependent graphs.
problem Uncertainty quantification for non-independent node-level predictions in graphs.
method Derives axioms for expected predictive uncertainty, proposes Graph Posterior Network (GPN) which performs Bayesian posterior updates.
result GPN outperforms existing approaches for uncertainty estimation in semi-supervised node classification.
Proposes a new framework for uncertainty evaluation in ML classification models.
problem Uncertainty evaluation for ML classification models not addressed by existing metrological guidelines.
method Develops a metrological framework based on probability mass functions and summary statistics.
result Extends the GUM to uncertainty for nominal properties, applicable to ML classification models.
New framework models uncertainty in classification debates.
problem Weak interpretability of existing uncertainty quantification methods.
method Courtroom analogy and Mixture of Dirichlet Experts (MoDEX) model.
result MoDEX achieves state-of-the-art uncertainty quantification performance.
Study examines how uncertainty visualization affects analyst trust in automated classification systems.
problem The impact of uncertainty on analyst trust in automated classification systems.
method Empirical study evaluating different active learning query policies and visualizations.
result Query policy significantly influences analyst trust in automated classification systems.
JUCAL jointly calibrates aleatoric and epistemic uncertainties in classifier ensembles.
problem Misrepresentation of predictive uncertainty due to unbalanced aleatoric and epistemic uncertainties.
method Joint Uncertainty Calibration (JUCAL) that jointly calibrates two constants to weight and scale uncertainties.
result Significantly outperforms state-of-the-art calibration methods across various text classification tasks.
Bayesian classification improves with explicit aleatoric uncertainty.
problem Lack of aleatoric uncertainty representation in Bayesian classification.
method Explicitly account for aleatoric uncertainty using a Dirichlet observation model.
result Explicit aleatoric uncertainty improves performance of Bayesian neural networks.
Robustness to out-of-distribution (OOD) data is an important goal in building reliable machine learning systems. Especially in autonomous systems, wrong predictions for OOD inputs can cause safety critical situations. As a first step towards a solution, we consider the problem of detecting such data in a value-based de…
Study evaluates uncertainty estimation methods in binary classification models.
problem Difficulty in quantifying uncertainty in complex models like deep learning.
method Approximate Bayesian inference with synthetic datasets and empirical tests.
result Deep learning-based algorithms do not consistently reflect lack of evidence for out-of-distribution data.
This work examines uncertainty sampling in binary classification using equivalent loss.
problem Lack of consensus on proper uncertainty definition and theoretical guarantees for active learning.
method Systematically examines uncertainty sampling via equivalent loss, proving its optimality.
result Established that uncertainty sampling optimizes against equivalent loss, providing theoretical guarantees.
Proposes a new batch selection method for multi-label classification.
problem Improving the accuracy of deep neural networks in multi-label classification tasks.
method Adapts uncertainty measures to multi-label data, considering label correlations and dynamic uncertainty.
result Improves performance and accelerates convergence of multi-label deep learning models.
DAEDL improves EDL's OOD detection and classification performance by integrating feature space density.
problem Limited OOD detection and classification performance of EDL.
method Integrates feature space density with EDL's output and uses a novel parameterization.
result Demonstrates state-of-the-art performance across uncertainty estimation and classification tasks.
New framework improves attribution of predictive uncertainties in classification models.
problem Improper attribution of predictive uncertainties in classification tasks.
method Combines path integrals, counterfactual explanations, and generative models.
result Framework outperforms existing alternatives in quantitative evaluations.
Paper predicts high-frequency futures return directions using mean-uncertainty methods.
problem Data imbalance in short-term price movements of futures markets.
method Employed mean-uncertainty logistic regression and support vector machines under sublinear expectation framework.
result Mean-uncertainty approaches outperform conventional methods in classification metrics and average returns.
Paper proposes a new method to quantify uncertainty in machine learning models.
problem Quantifying uncertainty in multiclass classification models.
method Distance-based approach using Integral Probability Metrics (IPMs).
result Effective uncertainty measures for multiclass classification.
CP-ROC bands improve graph classification accuracy and uncertainty quantification.
problem Uncertainty quantification and robustness to distributional shifts in graph classification.
method Conditional Prediction ROC (CP-ROC) bands for graph classification, developed for TGNNs and adaptable to GNNs.
result Statistically guaranteed coverage for CP-ROC under local exchangeability condition, improving prediction reliability.
CUQ-GNN adapts uncertainty quantification for graph data, improving on GPN.
problem Defining meaningful uncertainty on graph data with domain-specific characteristics.
method Combines Graph Neural Networks with Posterior Networks using Normalizing Flows.
result CUQ-GNN produces more flexible and effective uncertainty estimates.
The paper improves uncertainty quantification for node classification using distance-based regularization.
problem Uncertainty in deep learning models, especially for node classification tasks.
method Graph posterior networks (GPNs) with UCE loss function, followed by a distance-based regularization.
result The proposed distance-based regularization outperforms state-of-the-art methods in OOD detection and misclassification detection.
Paper introduces variance-based measures for second-order uncertainty quantification in classification problems.
problem Uncertainty in machine learning predictions and decision-making.
method Second-order uncertainty quantification using variance-based measures.
result Variance-based measures effectively quantify uncertainty on a class-based level and are competitive with entropy-based measures.
We consider the problem of uncertainty estimation in the context of (non-Bayesian) deep neural classification. In this context, all known methods are based on extracting uncertainty signals from a trained network optimized to solve the classification problem at hand. We demonstrate that such techniques tend to introduc…
Bayesian model improves classification performance with flexible uncertainty modeling.
problem Improving classification performance with flexible uncertainty modeling.
method Combines Gaussian process and Dirichlet process priors for latent function and link function, respectively.
result Outperforms standard logistic regression on simulated data.
Bayesian neural networks enhance uncertainty estimation in graph contrastive learning.
problem Uncertainty in graph contrastive learning when labeled data is scarce.
method Variational Bayesian neural networks for uncertainty estimation.
result Improved uncertainty estimation and downstream performance on semi-supervised node-classification tasks.
Uncertainty quantification for deep learning is a challenging open problem. Bayesian statistics offer a mathematically grounded framework to reason about uncertainties; however, approximate posteriors for modern neural networks still require prohibitive computational costs. We propose a family of algorithms which split…
A novel framework quantifies uncertainty using proper scores for various tasks.
problem Uncertainty quantification in machine learning for reliable applications.
method Proposes a general framework based on proper scores for epistemic, aleatoric uncertainty, and model calibration.
result Achieves state-of-the-art uncertainty estimation for large language models and generative models.
Scores measure certainty and doubt in classification predictions.
problem Quantitative uncertainty assessment in classification problems.
method Intuitive scores in Bayesian and frequentist frameworks.
result Measures assess and compare prediction quality and uncertainty.
Characterizes uncertainty in high-dimensional linear classification models.
problem Assessing uncertainty in high-dimensional linear classification models.
method Approximate message passing algorithm for posterior marginals, closed-form formula for joint statistics.
result Closed-form formula for joint statistics between logistic classifier, Bayesian uncertainty, and ground-truth probit uncertainty.
In this paper, we study the problem of deriving fast and accurate classification algorithms with uncertainty quantification. Gaussian process classification provides a principled approach, but the corresponding computational burden is hardly sustainable in large-scale problems and devising efficient alternatives is a c…
Efficient neural network ensembles improve image classification reliability and uncertainty quantification.
problem Uncertainty in neural network predictions for industrial image classification.
method Investigated efficient neural network ensembles (snapshot, batch, multi-input multi-output) for image classification reliability and uncertainty quantification.
result Batch ensemble is a cost-effective and competitive alternative to deep ensembles, offering savings in training and test time.
With the widespread success of deep neural networks in science and technology, it is becoming increasingly important to quantify the uncertainty of the predictions produced by deep learning. In this paper, we introduce a new method that attaches an explicit uncertainty statement to the probabilities of classification u…
New method quantifies uncertainty at class level for better decision-making.
problem Improving cost-sensitive decision-making in classification tasks.
method Label-wise decomposition of uncertainty measures based on non-categorical metrics.
result Proposed measures adhere to desirable properties and improve uncertainty quantification.
Classification of high dimensional data finds wide-ranging applications. In many of these applications equipping the resulting classification with a measure of uncertainty may be as important as the classification itself. In this paper we introduce, develop algorithms for, and investigate the properties of, a variety o…
New method corrects biased predictions and uncertainty estimates in classification with nuisance parameters.
problem Tackles biased predictions and invalid uncertainty estimates in classification with nuisance parameters.
method Proposes a method that estimates ROC across the entire nuisance parameter space to devise invariant cutoffs.
result Demonstrates effective domain adaptation and valid prediction sets with high power.
Proposes a novel graph self-training method with EM regularization for semi-supervised node classification.
problem Handles noisy graph structures and feature spaces in semi-supervised node classification.
method Introduces an Expectation-Maximization (EM) regularization scheme for uncertainty-aware pseudo-label generation and model retraining.
result Significantly outperforms strong baselines by up to 2.5% in accuracy.
CRUDE calibrates regression uncertainty without assuming specific error distributions.
problem Uncalibrated uncertainty estimates in regression models, especially for modern predictive tasks.
method CRUDE assumes error distributions have a constant shape, shifted and scaled by predicted mean and standard deviation.
result CRUDE produces sharper, better calibrated, and more accurate uncertainty estimates than existing methods.
New algorithm for uncertain time series classification.
problem Uncertainty in time series data.
method Uncertain dissimilarity measure based on Euclidean distance and uncertain shapelet transform.
result Effectiveness of the uncertain shapelet transform algorithm on state-of-the-art datasets.
Efficiently approximates uncertainty in classification models using Dirichlet distributions.
problem Inefficient computation of uncertainty estimates in Bayesian deep learning.
method Revised Laplace Bridge method to construct a Dirichlet approximation of softmax output distributions.
result The Dirichlet approximation leads to more efficient computation and better uncertainty estimates.
Paper introduces a new uncertainty measure for misclassification detection.
problem Effective detection of unreliable model predictions in machine learning.
method Data-driven measure of uncertainty relative to an observer based on soft-predictions.
result Demonstrates improved misclassification detection over state-of-the-art methods.
The wide and rapid adoption of deep learning by practitioners brought unintended consequences in many situations such as in the infamous case of Google Photos' racist image recognition algorithm; thus, necessitated the utilization of the quantified uncertainty for each prediction. There have been recent efforts towards…
New method reduces model bias and variance by adjusting training sample weights based on label uncertainty.
problem Tradeoff between model bias and variance in classification models.
method Estimate label uncertainty, adjust training sample weights, and fine-tune decision boundary.
result Improves model performance and reduces variance in physical activity recognition.
We study the quantification of uncertainty of Convolutional Neural Networks (CNNs) based on gradient metrics. Unlike the classical softmax entropy, such metrics gather information from all layers of the CNN. We show for the EMNIST digits data set that for several such metrics we achieve the same meta classification acc…
Bayesian neural networks improve SHD classification and uncertainty quantification.
problem Improving screening for structural heart disease using noninvasive ECG and echocardiography.
method Comparing frequentist and Bayesian neural network classifiers on the EchoNext dataset.
result Bayesian classifiers provide more robust uncertainty quantification.
Proposes a new method for localized uncertainty quantification in random forests using proximity measures.
problem Localized uncertainty quantification in random forests for improved reliability of predictions.
method Forming localized distributions of Out-Of-Bag (OOB) errors around nearby points defined by similarity measures (proximities) to create prediction intervals for regression and trust scores for classification.
result Localized prediction intervals and trust scores enhance model accuracy and provide higher accuracy-rejection AUC scores than competing methods.
TULiP estimates uncertainty for deep learning models safely.
problem Reliable uncertainty estimation for deep learning models in the open world.
method TULiP considers a hypothetical perturbation, bounds its effect, and computes uncertainty from sampled predictions.
result TULiP achieves state-of-the-art performance in OOD detection benchmarks.
ALIEN improves uncertainty estimation of language models by refining entropy-based methods.
problem Overconfidence in uncertainty estimation for language models, especially for difficult inputs.
method ALIEN refines entropy-based uncertainty by aligning it with prediction reliability, using a lightweight uncertainty head.
result ALIEN consistently outperforms strong baselines in detecting incorrect predictions and achieving the lowest calibration error.
Study on continuous sequence classification with distribution uncertainty.
problem Classifying continuous sequences with varying distribution uncertainty.
method Proposes distribution-free tests for three test designs: fixed-length, sequential, and two-phase tests.
result Error probabilities decay exponentially fast for all test designs.