New approach to robustly reliable learners against instance-targeted attacks.
problem Addressing data poisoning attacks on robustly reliable learners.
method Defining regularized robustly reliable learners and efficient algorithms.
result Efficient algorithms for robustly reliable learners with sublinear runtime.
A new framework decouples instance representation learning from subject-level supervision in EEG-based disease diagnosis.
problem Inherently assigning subject labels to all instances in EEG-based disease diagnosis leads to unreliable representations.
method BridgeMIL, a two-stage framework that pretrains an encoder without inherited instance labels and then applies subject-level supervision.
result BridgeMIL achieves the highest mean accuracy in 14 of 15 dataset-backbone settings, with an overall mean accuracy of 76.57%.
DW-KNN improves KNN by integrating distance and neighbor reliability for better prediction accuracy.
problem Standard KNN assumes all neighbors are equally reliable, leading to unreliable predictions in heterogeneous feature spaces.
method DW-KNN integrates exponential distance with neighbor validity, providing instance-level interpretability and reducing hyperparameter sensitivity.
result DW-KNN achieves 0.8988 average accuracy, ranks 2nd among six methods, and has the lowest cross-validation variance.
k-Rater reliability corrects under-reporting of aggregated data reliability.
problem Under-reporting of data reliability in aggregated ratings.
method k-Rater reliability (kRR) as a multi-rater generalization of IRR.
result kRR provides a more accurate measure of reliability for aggregated datasets.
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.
In many instances, information on engineering systems can be obtained through measurements, monitoring or direct observations of system performances and can be used to update the system reliability estimate. In structural reliability analysis, such information is expressed either by inequalities (e.g. for the observati…
Framework for reliable prediction errors using Test-Time Dropout and Conformal Prediction.
problem Lack of reliable error computation for deep neural networks in drug discovery.
method Training a single neural network with dropout, applying it multiple times to validation and test sets, generating ensemble predictions, and using Conformal Prediction to compute errors.
result Dropout Conformal Predictors are valid and efficient, with narrower confidence intervals than RF-based Conformal Predictors.
New framework detects unusual input-output associations in multivariate data.
problem Detecting conditional outliers in multivariate data.
method Decomposable conditional probabilistic model with component weights.
result Framework successfully identifies multivariate conditional outliers.
Paper proposes a method to generate instance labels from weakly supervised data.
problem Weakly supervised instance labeling in medical image analysis.
method Uses multiple instance learning (MIL) and knowledge distillation to generate instance-level predictions.
result Significantly outperforms state-of-the-art MIL methods in instance-level prediction.
CM algorithm improves MMI classifications for unseen instances.
problem Improving classification accuracy for unseen instances using MMI criterion.
method Introduces CM algorithm for MMI classifications, combining semantic and Shannon channels for matching.
result Achieves high mutual information (99%) with minimal iterations in low-dimensional feature spaces.
Active learning performance hard to assess during deployment.
problem Difficulty in estimating active learning performance during deployment.
method Formalized task, identified challenges, evaluated existing strategies.
result No reliable method to estimate active learning performance during training.
A new matrix factorization model learns and weights data deviations for better model performance.
problem Stochastic noise causes unreliable data points, leading to suboptimal model fitting.
method Deviation-driven matrix factorization model that learns and weights data deviations.
result Our model outperforms state-of-the-art models in accuracy and efficiency.
CPA framework assesses conditional validity of conformal prediction.
problem Challenges in evaluating conditional validity of conformal prediction.
method Reframes conditional coverage evaluation as a supervised learning task.
result Establishes convergence rates and proves CVI consistency.
CSI detects novelty by contrasting shifted instances, outperforming existing methods.
problem Detecting samples from outside the training distribution.
method Contrastive learning with distributionally shifted augmentations.
result CSI outperforms existing methods in various novelty detection scenarios.
Introduces UA attention to improve reliability of attention mechanisms in predictions.
problem Reliability of attention mechanisms in weakly-supervised learning.
method Introduces input-dependent uncertainty to attention mechanism and learns it using variational inference.
result Significantly outperforms existing attention models on risk prediction tasks.
GLOBE-CE offers efficient global counterfactual explanations.
problem Lack of reliable and scalable global counterfactual explanations.
method Translation-based approach for global counterfactual explanations.
result GLOBE-CE performs significantly better than current methods across multiple metrics.
Paper improves neural network accuracy by focusing on uncertain samples.
problem Improving neural network accuracy through better instance weighting.
method Estimates sample uncertainty in SGD to re-weight training instances.
result Reliable improvements in accuracy across various network architectures.
Paper proposes MUCS for more reliable TDA in diffusion models.
problem Current TDA approaches lack reliability and robustness.
method Mirrored unlearning and noise-consistent skew (MUCS).
result MUCS outperforms existing methods on three datasets.
Boosting for label ranking outperforms existing methods.
problem Improving label ranking predictions using boosting techniques.
method Proposed a boosting algorithm tailored for label ranking tasks.
result Significantly outperforms existing label ranking algorithms.
POTA improves short text clustering by generating reliable pseudo-labels.
problem Limited discriminative representations in short texts.
method POTA uses instance-level attention and optimal transport for semantic consistency and cluster structure.
result POTA outperforms state-of-the-art methods in short text clustering.
A new framework detects novel classes in data streams.
problem Detecting novel class labels in data streams.
method Semi-supervised multi-task learning framework for co-representation learning.
result Superior performance over existing methods on real-world datasets.
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.
New method selects features for sequential decision making.
problem Dynamic feature selection for instance-wise decisions.
method Latent variable model trained in a supervised manner; reasoning across stochastic latent space.
result Outperforms existing methods on various datasets.
In crowd labeling, a large amount of unlabeled data instances are outsourced to a crowd of workers. Workers will be paid for each label they provide, but the labeling requester usually has only a limited amount of the budget. Since data instances have different levels of labeling difficulty and workers have different r…
Proposes incorporating noise sources in machine learning evaluation for more reliable conclusions.
problem Inadequate handling of nondeterminism in machine learning research leads to unreliable results.
method Uses linear mixed effects models (LMEMs) and generalized likelihood ratio tests (GLRT) to analyze performance evaluation scores and assess performance differences.
result Demonstrates how to incorporate various sources of noise and data properties into statistical significance testing and reliability analysis.
New research shows that binary classification can be done with noisy data, but only if there are clean samples available.
problem Learning binary classification with instance and label dependent label noise.
method Theoretical analysis and empirical risk minimization.
result Empirical risk minimization achieves the optimal excess risk bound without additional assumptions.
Study examines flaws in probing LLMs' knowledge and introduces a new method.
problem Flaws in existing methods for probing the veracity of LLMs' internal knowledge.
method sAwMIL (Sparse-Aware Multiple-Instance Learning) combining multiple-instance learning with conformal prediction.
result LLMs encode a third type of signal distinct from true and false.
CNN learns diabetic syndromes from patient records.
problem Syndrome differentiation in TCM is complex and lacks standardization.
method Multi-instance multi-task learning with CNN.
result Outperforms other methods on diabetes dataset.
Convex programming framework generates adversarial examples for deep learning models.
problem Generating robust adversarial examples for deep learning models.
method Convex programming for perturbation analysis of deep learning architectures.
result Framework can generate adversarial examples with competitive performance.
Improved interpretability methods for ML models using local regressions and variable importance.
problem Inability of existing interpretability methods to provide reliable explanations for ML models, especially in high-dimensional problems with irrelevant features and non-linear relationships.
method Introduces VarImp and SupClus methods using local regressions with weighted distance considering variable importance.
result VarImp and SupClus methods yield better explanations than state-of-the-art approaches, especially in high-dimensional problems with irrelevant features and non-linear relationships.
This study revisits UQ validation methods based on consistency and adaptivity concepts.
problem Lack of comprehensive validation methods for UQ metrics across input feature ranges.
method Revisit and extend common validation methods for UQ metrics based on consistency and adaptivity concepts.
result Improved understanding and capabilities of UQ metrics validation methods.
The paper improves robust optimization by introducing margin theory.
problem Improving the reliability of solutions in high-dimensional robust optimization.
method Introducing margin theory to improve sample complexity and reliability of solutions.
result The sample complexity of a class of random programs does not depend on the number of variables.
New system detects pain from facial AU combinations using MIL and MCIL.
problem Detecting pain from facial expressions reliably.
method Weakly supervised learning, multiple instance learning, multiple clustered instance learning.
result 87% pain recognition accuracy on UNBC-McMaster Shoulder Pain Expression dataset.
Crowdsourced training of large neural networks with decentralized Mixture-of-Experts.
problem Expensive training of large neural networks limits research contributions.
method Learning@home: decentralized Mixture-of-Experts for large, poorly connected participants.
result Performance and reliability of Learning@home surpass conventional distributed training.
Deep learning method segments and monitors slums from satellite imagery.
problem Slum rehabilitation and improvement in developing countries.
method Regional convolutional neural networks for instance segmentation using transfer learning.
result Maximum AP of 80.0 for slum shape and appearance learning.
CGP predicts counterfactuals to improve decision-making reliability.
problem Reliability of supervised learning models in predicting future outcomes.
method Introducing CGP to predict counterfactuals instead of outcomes under an existing policy.
result CGP improves decision-making in temporal settings by predicting future trajectories under sequences of actions.
Paper introduces active Bayesian method for assessing black-box classifiers efficiently.
problem Need to assess performance of black-box classifiers reliably with limited labels.
method Develops inference strategies and proposes active Bayesian framework for efficient instance selection.
result Significant gains in performance assessment with fewer labels compared to traditional methods.
New deep learning framework for tabular data clusters with interpretable features.
problem Need for reliable and interpretable clustering models for tabular data.
method Self-supervised feature selection and gate matrix for cluster-level feature selection.
result Model provides interpretable cluster assignments with driving features.
This work introduces a bias-variance decomposition for proper scores, improving uncertainty estimation in predictive models.
problem Reliable uncertainty estimation for predictions in safety-critical applications, especially under domain drift.
method Developed a general bias-variance decomposition for proper scores, introducing the Bregman Information as the variance term.
result The decomposition provides novel formulations for different predictive tasks, including classification and model ensembles.
Interprets deep CNN models via meta-learning.
problem Non-interpretable deep CNN models in machine learning.
method Meta-learning approach using clustering and Random Forest.
result Achieves global interpretation without sacrificing accuracy.
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%.
New method calibrates neural network predictions for better reliability.
problem Improper probability estimates from deep networks leading to unreliable predictions.
method Proposes a constrained optimization approach for a monotonic calibration map.
result Achieves state-of-the-art performance across various datasets and models.
Flow Matching enables robust training of CNFs with various probability paths.
problem Training Continuous Normalizing Flows (CNFs) at large scales.
method Flow Matching (FM) is a simulation-free approach for training CNFs by regressing vector fields of conditional probability paths.
result Flow Matching with diffusion paths yields more robust and stable training compared to diffusion-based methods.
Study selective classification with limited feedback in online learning.
problem Resource-limited and safety-critical domains where feedback is only received on abstentions.
method Versioning-based schemes for minimizing mistakes and abstentions.
result Constructed schemes that make few mistakes and minimal excess abstentions.
New method R-LOCO improves local feature importance analysis.
problem Local attribution methods fail to accurately identify important features.
method R-LOCO segments input space into regions and applies global methods within.
result R-LOCO delivers more accurate local attributions.
Improves global counterfactual explanations for model recourse.
problem Inability to provide explanations beyond local instances.
method Investigates and improves Actionable Recourse Summaries (AReS) for global counterfactual explanations.
result Develops more efficient and interactive explainability tools.
Proposes a VAE for HDLSS data augmentation.
problem Data augmentation in HDLSS settings with small sample sizes.
method Geometry-based variational autoencoder with latent space modeling.
result Significant improvement in classification metrics (e.g., balanced accuracy from 66.3% to 74.3%).
Paper improves short text clustering by integrating semantic relationships into Optimal Transport.
problem Erroneous pseudo-labels caused by neglecting semantic consistency in existing OT methods.
method Designs an instance-level attention mechanism to capture semantic relationships and integrates them into the OT formulation.
result Generates reliable pseudo-labels that improve clustering accuracy.