GOOWE-ML ensemble improves multi-label stream classification.
problem Online multi-label data stream classification.
method Novel online stacked ensemble with spatial weighting.
result GOOWE-ML ensembles outperform other models in predictive performance.
Study proposes an ensemble learning method to improve multi-label classification performance.
problem Improving multi-label classification performance in machine learning.
method Ensemble learning approach using multiple base-level algorithms.
result Proposed method outperforms base-level algorithms in multi-label classification.
ML-KFHE improves multi-label classification performance using Kalman filter fusion.
problem Lack of effective multi-label ensemble classification methods.
method Exploits Kalman filter sensor fusion properties for multi-label classification.
result Significantly improved predictive performance on multi-label datasets.
Proposes a new method for deep ensembles that improves accuracy and calibration.
problem Improving accuracy and calibration of deep ensembles.
method Estimates confusion matrices of ensemble members and weighs them according to their inferred performance.
result Empirically shows superiority of soft Dawid Skene over ensemble averaging.
Paper proposes a progressive ensemble network for zero-shot image recognition.
problem Challenges of zero-shot learning due to lack of labeled data and expanding categories.
method Proposes a progressive ensemble network with multiple projected label embeddings.
result Demonstrates improved zero-shot image recognition performance on multiple datasets.
New approach uses under-trained deep ensembles to learn from noisy labels.
problem Improper labelling hinders reliable generalization in supervised learning.
method Under-trained deep ensembles, each trained on a subset of data, combine to form better labels.
result Significant performance improvement in accuracy and kappa for noisy label tasks.
This work improves SSL by leveraging disentangled latent space for better self-ensembling.
problem Improving semi-supervised learning performance with limited labeled data.
method Stacked SSL model using unsupervised disentangled representation learning for stochastic embedding.
result Improved performance and interpretability of disentangled representations over related SSL models.
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.
Neural network with loss ensemble improves text classification accuracy.
problem Improving text classification accuracy in noisy environments.
method Extended neural network with an ensemble loss function, weights tuned through gradient propagation.
result Improvement in classification accuracy and resilience against label noise.
KFHE uses Kalman filters to improve ensemble classification accuracy.
problem Improving multi-class ensemble classification accuracy.
method KFHE treats ensemble training as a state estimation problem using Kalman filters.
result KFHE outperforms state-of-the-art algorithms in noisy and clean datasets.
Ensemble methods for supervised machine learning have become popular due to their ability to accurately predict class labels with groups of simple, lightweight "base learners." While ensembles offer computationally efficient models that have good predictive capability they tend to be large and offer little insight into…
The recently proposed Temporal Ensembling has achieved state-of-the-art results in several semi-supervised learning benchmarks. It maintains an exponential moving average of label predictions on each training example, and penalizes predictions that are inconsistent with this target. However, because the targets change …
EnMDAP aligns conditional distributions for multi-source domain adaptation using pseudolabels.
problem Training a target model with no labeled data in the absence of target data labels.
method EnMDAP uses label-wise moment matching and ensemble learning with multiple feature extractors.
result EnMDAP achieves state-of-the-art performance in multi-source domain adaptation tasks.
SELF filters noisy labels to improve deep learning performance.
problem Overfitting to noisy labels in deep learning.
method Self-ensemble label filtering (SELF) using running averages of predictions.
result SELF improves task performance by filtering noisy labels dynamically.
A new ensemble of Gaussian processes improves active learning efficiency.
problem Efficiently labeling data in high-cost domains like medical imaging.
method Adaptive weighted ensemble of Gaussian processes (EGP) for active learning.
result EGP-based approaches outperform single GP-based active learning methods.
SUMMA aggregates predictions without labeled data.
problem Lack of labeled data limits ensemble methods.
method Developed SUMMA framework for unlabeled data.
result Estimates base classifier performances and optimal ensemble strategy.
Self-paced ensemble learning improves audio classification models.
problem Improving performance of individual models in speech and audio classification.
method A self-paced ensemble learning scheme where models learn from each other over several iterations.
result SPEL significantly outperforms baseline ensemble models.
FUSE improves verification quality without ground truth labels.
problem Verification of model outputs using imperfect judges and reward models.
method Ensembling verifiers without ground truth labels using spectral algorithms.
result FUSE matches or improves upon semi-supervised alternatives in test-time scaling experiments.
Ensemble unsupervised anomaly detection using IRT for hidden ground truth.
problem Challenges in constructing an ensemble from unsupervised anomaly detection methods.
method Use Item Response Theory to compute latent traits and construct an ensemble that downplays noisy methods.
result Demonstrated effectiveness of IRT ensemble on extensive data repository.
Multi-label classification has attracted an increasing amount of attention in recent years. To this end, many algorithms have been developed to classify multi-label data in an effective manner. However, they usually do not consider the pairwise relations indicated by sample labels, which actually play important roles i…
FASE-AL uses active learning to reduce labeling costs for data streams.
problem Reduction of labeling costs for data stream classification.
method Combines Fast Adaptive Stacking of Ensembles (FASE) with active learning.
result Achieves high accuracy with minimal labeled data.
UNREAL selectively ensembles distinct models to improve active learning performance.
problem Difficulty in distinguishing genuine uncertainty from noise in limited labeled data.
method Selective ensembling of distinct models from the Rashomon set.
result UNREAL achieves faster convergence and up to 20% predictive accuracy improvement.
DEBAL uses ensemble methods to improve deep Bayesian active learning in image classification.
problem Mode collapse issue in Monte Carlo dropout for deep CNNs.
method Proposes DEBAL, an ensemble-based active learning strategy for deep neural networks.
result DEBAL improves deep Bayesian active learning, capturing superior data uncertainty and faster convergence.
Paper introduces SUEL model for integrating predictors without labeled data.
problem Combining predictors with unknown accuracy and high correlation.
method Structured unsupervised ensemble learning (SUEL) with correlation-based decomposition algorithms.
result Efficient integration of dependent predictors without labeled data.
Active learning improves anomaly detection by tuning ensembles with true labels.
problem Configuring anomaly detectors for minimal effort on false positives.
method Compact description, data drift detection, active learning strategies.
result Active learning significantly improves anomaly discovery and adapts to streaming data.
GLAD learns local relevance of global anomaly detectors via human feedback.
problem Improving explainability and local relevance of global anomaly detectors.
method A human-in-the-loop learning algorithm that adjusts the local relevance of anomaly detection ensemble members using label feedback.
result GLAD effectively learns local relevance and discovers anomalies via label feedback.
Unsupervised models can provide supplementary soft constraints to help classify new target data under the assumption that similar objects in the target set are more likely to share the same class label. Such models can also help detect possible differences between training and target distributions, which is useful in a…
Voting ensemble of robust models improves robustness.
problem Improving robustness of defensive models against adversarial attacks.
method Hard-label voting ensemble of pretrained robust models.
result Voting ensemble can boost robust error over individual models.
Proposes HetSNGP method for joint model and data uncertainty modeling.
problem Uncertainty estimation in deep learning for safety-critical applications.
method Jointly models model and data uncertainty with HetSNGP method.
result Outperforms baseline methods on challenging out-of-distribution datasets.
A new weighting scheme corrects label ensembles in multi-label classification.
problem Improving the reliability of multi-label classification with imbalanced data.
method Proposed a novel weighting scheme based on fuzzy confusion matrix and information theory.
result The proposed method reduces the vulnerability to imbalanced class distribution and improves classification quality.
Improved YouTube-8M classification accuracy using ensemble methods.
problem Improving video classification accuracy on YouTube-8M dataset.
method Ensemble methods to improve baseline predictions.
result Global prediction accuracy (GAP) increased from 77% to 80.7%.
A new method for synthetic oversampling of multi-label data focusing on local label distribution.
problem Class imbalance in multi-label datasets affects prediction accuracy.
method Proposes a new method for synthetic oversampling of multi-label data focusing on local label distribution.
result Demonstrates effectiveness in generating more diverse and better labeled instances.
LEC prevents deep nets from memorizing noisy examples.
problem Deep nets overfit to noisy data.
method LEC removes noisy examples based on an ensemble of perturbed networks.
result LTEC outperforms state-of-the-art on noisy MNIST, CIFAR-10, and CIFAR-100.
Proposes methods to improve multi-label learning by addressing local label imbalance.
problem Local label imbalance within minority class examples degrades multi-label learning performance.
method Introduces a measure to assess local label imbalance and two sampling approaches (MLSOL, MLUL) to address it.
result Experimental results show MLSOL and MLUL improve performance on multi-label datasets.
Ensemble methods have been shown to be an effective tool for solving multi-label classification tasks. In the RAndom k-labELsets (RAKEL) algorithm, each member of the ensemble is associated with a small randomly-selected subset of k labels. Then, a single label classifier is trained according to each combination of ele…
Specialists outperform generalists in ensemble classification.
problem Determining the accuracy of an ensemble of classifiers when individual classifier accuracies are known.
method Proved upper and lower bounds on ensemble accuracy, constructed specialist and generalist classifiers.
result Upper and lower bounds on ensemble accuracy, practical implications for classifier construction.
Vote-boosting is a sequential ensemble learning method in which the individual classifiers are built on different weighted versions of the training data. To build a new classifier, the weight of each training instance is determined in terms of the degree of disagreement among the current ensemble predictions for that i…
A new confidence measure improves self-training in biased data.
problem Improving self-training in biased data.
method Proposes a new confidence measure, T-similarity, based on ensemble diversity of linear classifiers.
result Empirically shows the benefit of T-similarity for pseudo-labeling policies on various datasets.
Active stacking improves heart rate estimation accuracy with minimal labeled data.
problem Inconsistent heart rate estimation across subjects due to signal quality and individual differences.
method Active learning and stacking ensemble regression to aggregate base estimators.
result Active stacking significantly outperforms other methods with minimal labeled data.
SNTG improves semi-supervised learning by considering data connections.
problem Improving semi-supervised learning performance with fewer labeled data.
method Constructs a graph from teacher model predictions and learns smooth representations of similar neighboring points.
result Achieves state-of-the-art results on semi-supervised learning benchmarks.
A blind scheme combines multiple classifiers without knowing their training labels.
problem Combining multiple classifiers to achieve high performance.
method Moment matching method using tensor and matrix factorization.
result Proposed blind scheme outperforms known methods on synthetic and real datasets.
A method for clustering using transfer learning from similar labeled data.
problem Clustering with datasets having different features and labeled data.
method Constructing meta-features to describe structural characteristics of data and transferring them between source and target domains.
result The method is efficient and works under arbitrary feature descriptions of source and target domains with smaller complexity.
Proposes a deep tree-ensemble model for multi-output prediction.
problem Lack of efficient solutions for multi-output prediction.
method Integrates tree-embeddings into deep tree-ensembles for structured output prediction.
result Superior performance in multi-label classification and multi-target regression tasks.
The paper develops a student performance prediction model using ensemble methods.
problem Improving student performance prediction in high school courses.
method Developed a multilabel classification model using SVM, RF, KNN, and MLP. Improved performance with LP transformation and partitioning schemes.
result The model achieved better performance than binary relevance and classifier chains.
Unsupervised ensemble classification for dependent data.
problem Classifying data with dependencies using multiple classifiers.
method Developed algorithms for sequential and networked data dependencies, using moment matching and Expectation Maximization.
result Improved classification performance on synthetic and real datasets.
Two modifications improve classifier chains for multi-label classification.
problem Discrepancy between training and testing feature spaces in classifier chains.
method Proposed modifications to address attribute noise.
result Improved prediction performance in challenging cases.
EC3 combines clustering and classification for better ensemble learning performance.
problem Combining classification and clustering for improved prediction performance.
method EC3 merges classification and clustering using an optimization function and block coordinate descent.
result EC3 outperforms other methods by at most 10% in AUC on 13 benchmark datasets.
The paper classifies market states to predict trading strategies, outperforming traditional methods.
problem Directly predicting prices or returns is unreliable; classifying market states is a better approach.
method Classify market states using various labels and features, then combine probabilities from neural networks.
result Trading strategy ensembles outperform traditional methods in returns and risk-adjusted returns.