Novel framework for reliable long-tailed classification.
problem Challenges of long-tailed imbalance and specific error risks.
method Bayesian Decision Theory and variational optimization.
result Demonstrates reliability and flexibility in diverse tasks.
Proposes a new method to interpret EEG classification models without needing a baseline.
problem Reliable interpretation of EEG classification models using integrated gradients.
method Compensated Integrated Gradients using Shapley sampling.
result The proposed method provides more reliable attributions than original integrated gradients.
Study evaluates consistency of LLMs in binary text classification, providing systematic guidance.
problem Lack of reliable methods for evaluating large language model (LLM) binary text classification.
method Adapting psychometric principles, the study determines sample size requirements, develops metrics for invalid responses, and evaluates intra- and inter-rater reliability.
result LLMs demonstrated high intra-rater consistency, achieving perfect agreement on 90-98% of examples, with smaller models outperforming larger counterparts.
Bayesian method improves reliability of BERT for hate speech detection.
problem Reliable detection of hate speech in user-generated content.
method Bayesian approach using Monte Carlo dropout in transformer models.
result Monte Carlo dropout provides well-calibrated reliability estimates.
BeMF improves recommendation reliability in recommender systems.
problem Improving reliability in recommender systems beyond accuracy.
method Bernoulli Matrix Factorization (BeMF) for model-based collaborative filtering.
result BeMF selects more reliable predictions, improving recommendation quality.
m-arcsinh improves SVM and MLP reliability and speed in scikit-learn.
problem Improving SVM and MLP reliability and speed in scikit-learn.
method Modified arcsinh function for kernel and activation in SVM and MLP.
result Competitive classification performance and reliability of SVM and MLP with m-arcsinh.
New model predicts hate speech with uncertainty estimates.
problem Detect and explain hate speech without restricting free speech.
method Adapted deep neural networks with Monte Carlo dropout.
result Models can reliably assess when texts are borderline.
The paper proposes a method to improve random forest classification accuracy by weighting trees based on their decision path reliability.
problem Random forests' uniform voting fails to correct errors in regions where incorrect tree representations outnumber correct ones.
method The paper introduces using the structural pattern of each tree's decision path as an instance-adaptive reliability signal to identify and weight more reliable trees.
result Using the proposed method yields a statistically significant accuracy improvement over RF on 36 binary classification benchmarks.
Crowdsourcing utilizes the wisdom of crowds for collective classification via information (e.g., labels of an item) provided by labelers. Current crowdsourcing algorithms are mainly unsupervised methods that are unaware of the quality of crowdsourced data. In this paper, we propose a supervised collective classificatio…
This paper considers the classification of linear subspaces with mismatched classifiers. In particular, we assume a model where one observes signals in the presence of isotropic Gaussian noise and the distribution of the signals conditioned on a given class is Gaussian with a zero mean and a low-rank covariance matrix.…
Optimal selective classification using likelihood ratios improves model reliability.
problem Enhancing predictive model reliability by allowing uncertain predictions.
method Neyman--Pearson lemma applied to likelihood ratios for optimal selection.
result Neyman--Pearson-informed methods outperform existing baselines under covariate shifts.
Neural eliminators reduce unreliable classification by eliminating improbable classes.
problem Unreliable classification due to noise, insufficient data, overlapping distributions, and unclear class definitions.
method Construct eliminators using classifiers with modified error functions, assigning cases to multiple classes instead of one.
result Elimination of improbable classes improves classification accuracy in real-life medical applications.
New method improves semi-supervised learning with missing labels.
problem Reliable classification with missing labels in semi-supervised learning.
method Develops a new semi-supervised learning approach that relaxes assumptions about unlabeled data.
result Provides classifiers that reliably quantify label uncertainty.
Bayesian framework improves deep classifier reliability.
problem Overconfident models under dataset shift.
method Bayesian inference with out-of-distribution data augmentation.
result Reliable uncertainty estimates for deep classifiers.
Improved reliability of machine learning predictions using variational auto-encoders.
problem Individual unreliability of machine learning models.
method Modified variational auto-encoders to identify a low-dimensional space for reliable classification.
result Improved reliability of predictions and robust identification of adversarial samples.
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.
Study improves reliability of neural models for virtual screening.
problem Reliability issues in neural models for molecular property prediction.
method Investigated model architectures, regularization, and loss functions.
result Correct choice of regularization and inference methods improves reliability.
CAT framework improves AI medical screening fairness and reliability.
problem Imbalanced data, varying performance across cohorts, and patient-level inconsistencies in traditional metrics.
method CAT framework introduces patient-level assessment, entropy-based distribution weighting, and cohort-weighted sensitivity and specificity.
result Enhanced predictive reliability, fairness, and interpretability of AI-driven medical screening models.
This paper studies the classification of high-dimensional Gaussian signals from low-dimensional noisy, linear measurements. In particular, it provides upper bounds (sufficient conditions) on the number of measurements required to drive the probability of misclassification to zero in the low-noise regime, both for rando…
A framework for detecting out-of-distribution data in RL using uncertainty-based classification.
problem Detecting out-of-distribution data in deep reinforcement learning systems.
method A one-class classification problem approach based on epistemic uncertainty reduction.
result The proposed UBOOD framework reliably detects out-of-distribution situations when combined with ensemble-based uncertainty estimators.
Paper introduces conformal prediction for reliable uncertainty quantification in landmark localization.
problem Systematic underestimation of total predictive uncertainty in landmark localization.
method Conformal prediction framework for multi-output regression, generating flexible prediction regions.
result Methods outperform existing approaches in validity and efficiency across 2D and 3D datasets.
Study analyzes and enhances robustness of neural networks for classification and regression.
problem Understanding and improving robustness of neural network predictions.
method Computes reachable sets of neural networks using over- and under-approximations.
result Approach outperforms adversarial attacks and state-of-the-art classifier verification methods.
Method cleans noisy training labels for biomedical data.
problem Accurately labeling biomedical data is challenging.
method Reliability-based training data cleaning with inductive conformal prediction.
result Significant enhancements in classification performance across multiple tasks.
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.
Bayesian learning improves reliability of molecular predictions for hit compound discovery.
problem Improving reliability of machine learning predictions for virtual screening.
method Bayesian learning algorithms applied to graph neural networks.
result Bayesian learning leads to well-calibrated predictions and higher hit compound success.
PEOC uses policy entropy to detect untrained states in RL.
problem Detecting untrained states in reinforcement learning for safety.
method Policy entropy based one-class classifier.
result PEOC is highly competitive and reliable.
The paper proposes a method to calibrate healthcare AI models for reliability and interpretability.
problem Characterizing model reliability and enabling introspection of model behavior in clinical decision making.
method A calibration-driven learning method combined with interpretability techniques based on counterfactual reasoning.
result Demonstrates the effectiveness of the proposed approach using a lesion classification problem with dermoscopy images.
New framework uses conformal predictions for robust, scalable machine learning classification.
problem Developing robust and reliable machine learning models for classification.
method Introducing scalable classifiers linked to statistical order theory and probabilistic learning theory, defining a score function and conformal safety set.
result Demonstrated practical implications in cybersecurity for identifying DNS tunneling attacks.
Algorithm learns binary function efficiently under arbitrary covariate shift.
problem Learning binary function under arbitrary distributions P and Q.
method PQ-learning algorithm using reliable learner with selective classification.
result Polynomial-time algorithm for covariate shift learning.
Paper tackles uncertainty in GNNs for graph data.
problem Uncertainty in GNNs' predictions for graph data.
method CF-T2NN, tensor decomposition, topological learning.
result CF-T2NN improves reliability and interpretability of GNN outcomes.
Develops a new tensor classification method for high-dimensional data.
problem Efficient learning algorithms exploiting tensorial structure in high-dimensional multi-way arrays.
method Tensor Train Multi-way Multi-level Kernel (TT-MMK) combining Canonical Polyadic decomposition, Dual Structure-preserving Support Vector Machine, and Tensor Train approximation.
result The TT-MMK method provides higher prediction accuracy and is more reliable computationally compared to other techniques.
Develops geometric framework for uncertainty-aware multi-class classification.
problem Silent failure of AI models when uncertain, especially in multi-class settings.
method Geometric framework treating probability vectors as points on the (c−1)-dimensional probability simplex, using Fisher--Rao metric for calibration and uncertainty quantification. result Empirical validation shows 72.5% of errors captured while deferring 34.5% of ambiguous predictions, reducing automated decision error rates from 16.8% to 6.9%.
Method generates uncertainty measures for street scene segmentation.
problem Reliability and uncertainty measures in semantic segmentation of street scenes.
method Nested crops, neural network segmentation, post-processing, uncertainty heat maps.
result Significant improvements in classification and regression performance.
Quantum classification robustness improved via quantum hypothesis testing.
problem Vulnerability of quantum classification algorithms to input perturbations.
method Formalized link between quantum hypothesis testing and robustness, developed practical protocols.
result Tight robustness condition independent of noise source (natural or adversarial).
Symmetric losses improve classifier robustness from corrupted labels.
problem Improving classifier performance from corrupted labels.
method Symmetric losses that satisfy a certain condition.
result Symmetric losses enhance robust classification from corrupted labels.
HCC extends conformal prediction to handle class hierarchies, improving prediction reliability.
problem Uncertainty quantification in classification models with class hierarchy considerations.
method Formulates HCC as a constrained optimization problem, ensuring coverage guarantees with a smaller subset of candidate solutions.
result HCC produces more reliable prediction sets by leveraging class hierarchy information.
The majority of traditional classification ru les minimizing the expected probability of error (0-1 loss) are inappropriate if the class probability distributions are ill-defined or impossible to estimate. We argue that in such cases class domains should be used instead of class distributions or densities to construct …
The paper decomposes probabilistic scores into reliability, uncertainty, and information loss.
problem Understanding the reliability and uncertainty of probabilistic predictions.
method Developed decomposition identities for proper losses, quantifying reliability, residual uncertainty, and information gain.
result A three-term identity for classification scores, revealing miscalibration, grouping term, and feature-level uncertainty.
New approach links machine learning reliability to epistemic uncertainty.
problem Characterize and quantify reliability of machine learning predictions.
method Extend JTB theory to neural networks, linking prediction reliability to support characteristics.
result Demonstrates reliability for individual predictions and identifies regions of uncertainty.
Improved DL models robust against adversarial attacks for wireless signal classification.
problem Adversarial attacks on deep learning-based wireless signal classifiers.
method Knowledge distillation and network pruning followed by adversarial training.
result Proposed models achieve better robustness and higher accuracy than standard models.
Improves model calibration for deep neural networks using proper scores.
problem Calibration errors in deep neural networks are often biased and inconsistent.
method Introduces proper calibration errors related to proper scores.
result Demonstrates the superiority of proper scores over common estimators.
Framework detects brain tumors robustly from MRI images.
problem Low clinical incidence of brain tumor cases makes diagnosis challenging.
method YOLOv8n for detection, DeiT for classification, PTP metric for evaluation.
result F1-score of 0.92 achieved with reduced computational resources.
Study improves image-caption retrieval by quantifying feature and posterior uncertainty.
problem Improving reliability in image-caption retrieval tasks with deep learning models.
method Quantified feature and posterior uncertainty for model averaging and reliability measure in image-caption retrieval.
result Consistent improvement in retrieval performance with different datasets and architectures.
Bayesian deep learning ensemble improves pneumonia diagnosis accuracy.
problem Manual, time-consuming pneumonia diagnosis with high inter-observer variability.
method Multi-level ensemble classification system using Bayesian Deep Learning.
result Accuracy of 98.06% in differentiating four pathologies.
This work evaluates and improves calibration of probabilistic classifiers.
problem Ensuring probabilistic classifiers output consistent probabilities with empirical frequencies.
method Develops a theoretical framework grounded in probability theory and proposes new evaluation techniques.
result Refined interpretations and new ways to quantify and visualize miscalibration.
New method reduces labeler costs by aggregating predictions from local classifiers.
problem Reduce labeler costs in multiclass classification.
method Model K-class classification using smaller classifiers trained on subsets of tasks. result Near-optimal scheme for designing classifier configurations reduces labeler costs.
New algorithms learn from comparisons to classify data robustly to noise.
problem Learning robust classifiers from noisy data efficiently.
method Introducing comparison queries to active learning, providing noise-tolerant classifiers.
result First time and query efficient algorithms for robust learning under bounded noise.
Improves AI-prior reliability for Bayesian inference.
problem Error propagation from predictive models into posterior inference.
method Rectified AI-informed prior elicitation framework.
result Significant reduction in bias and improvement in predictive performance.