Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

86173259345 · Jun 202019922001200920182026
48 results for supervised labels

Self-supervised attention model improves weakly labeled audio event classification.

problem Efficiently classify audio events with minimal labeled data.
method Develops a self-supervised attention model for weakly labeled audio clips.
result Self-supervised attention model performs comparably to strongly supervised model trained with strong labels.

PLRM synthesizes labels from mismatched sources for better training sets.

problem Creating labeled training sets is a major challenge in machine learning.
method PLRM uses probabilistic modeling to synthesize labels from indirect supervision sources with different output spaces.
result PLRM outperforms baselines by 2%-9% on various tasks.

A new semi-supervised learning method using label gradients.

problem Improve accuracy in semi-supervised learning with limited labeled data.
method Impute labels for unlabeled data using a distance metric based on model gradients, then optimize these imputed labels.
result Demonstrates state-of-the-art accuracy in semi-supervised CIFAR-10 classification.

Curriculum Labeling improves semi-supervised learning with pseudo-labeling, achieving high accuracy with minimal labeled data.

problem Improving semi-supervised learning with limited labeled data.
method Applying curriculum learning principles and restarting model parameters before each self-training cycle.
result 94.91% accuracy on CIFAR-10 with only 4,000 labeled samples.

New framework combines semi-supervised data programming with subset selection for improved text classification.

problem Sub-optimal performance in data programming with noisy labelling functions.
method Introduces a framework \model for semi-supervised data programming that uses joint models and subset selection.
result Significantly outperforms state-of-the-art on seven datasets.

Study shows semi-supervised learning can be more robust with fewer labeled examples.

problem Learning robust predictors in semi-supervised PAC model with minimal labeled data.
method Characterizes the minimal labeled and unlabeled data required for robust learning.
result Proves nearly matching upper and lower bounds on labeled sample complexity.

A new method for weakly supervised learning that improves model accuracy.

problem Training machine learning models with precise labels is expensive; weak supervision provides a low-cost alternative.
method Data consistent weak supervision algorithm that searches over classifiers to find plausible labelings, considering features of the training data and estimating labels for low/no coverage data.
result Empirically, the method significantly outperforms state-of-the-art weak supervision methods on text and image classification tasks.

Study shows adding unlabelled data improves semi-supervised image segmentation accuracy.

problem Improving semi-supervised image segmentation accuracy with limited labelled data.
method Investigated the impact of varying labelled and unlabelled data quantities in a semi-supervised segmentation algorithm.
result Significantly higher segmentation accuracy achieved with semi-supervised approach compared to supervised learning.

New method for semi-supervised learning in federated learning with and without labels at clients.

problem Training federated learning models with partially or completely unlabeled data.
method Federated Matching (FedMatch) with inter-client consistency loss and disjoint learning.
result FedMatch outperforms local semi-supervised learning and naive federated learning combinations.

Study shows imbalanced labels can be beneficial but not always in class-imbalanced learning.

problem Challenges in class-imbalanced learning with heavy label bias.
method Systematic investigation of semi-supervised and self-supervised approaches to leverage imbalanced labels.
result Imbalanced labels are valuable in semi-supervised learning but not always in self-supervised learning.

Paper introduces methods for more reliable probabilistic predictions with confidence intervals.

problem Inaccurate labeling of datasets due to unreliable probabilistic predictions from weak labeling functions.
method Proposes a methodology to provide confidence intervals for label probabilities using uncertainty sets of distributions.
result Improves reliability of probabilistic predictions and provides confidence intervals for label probabilities.

Unified model combines feature and label propagation for semi-supervised classification.

problem Combining feature and label propagation for effective semi-supervised classification.
method Unified Message Passing Model (UniMP) using Graph Transformer and masked label prediction.
result Obtains new state-of-the-art results in Open Graph Benchmark (OGB).

A new SS-SOM method combines unlabeled and labeled data for clustering and classification.

problem Combining unlabeled and labeled data for clustering and classification in high-dimensional datasets.
method Semi-Supervised Self-Organizing Map (SS-SOM) that dynamically switches between supervised and unsupervised learning.
result SS-SOM outperforms other methods in low-labeled sample conditions and achieves good results with all labeled samples.

Framework for training complex models using weak, noisy labels from multiple tasks.

problem Training complex models with limited labeled data.
method Multi-task weak supervision framework, solving matrix completion problem to recover task accuracies.
result Significant accuracy gains (20.2 points) over traditional supervised methods.

A new framework for semi-supervised learning using pseudo-representation labeling.

problem Improving deep learning models with limited labeled data.
method Pseudo-representation labeling framework integrating pseudo-labeling and self-supervised representation learning.
result Outperforms state-of-the-art semi-supervised learning methods in industrial classification problems.

Big models pretrain and fine-tune for semi-supervised learning on ImageNet.

problem Learning from few labeled examples with a large amount of unlabeled data.
method Unsupervised pretraining of a big ResNet model followed by supervised fine-tuning and distillation.
result 73.9% ImageNet top-1 accuracy with just 1% of labels (\le13 labeled images per class).

Study evaluates graph-based semi-supervised learning under noisy label conditions.

problem Evaluation of semi-supervised learning algorithms under noisy label conditions.
method Compared graph-based semi-supervised algorithms under varying labeled data and label noise conditions.
result Laplacian Eigenmaps performed better than label propagation under noisy conditions.

Improved audio classification with limited labels using multitask and self-supervised learning.

problem Limited labeled data for audio classification.
method Multitask learning and self-supervised learning on unlabeled data.
result Significant improvement in performance (up to 6%) through multitask and self-supervised learning.

New particle-based method improves semi-supervised learning robustness to label noise.

problem Label noise degrades semi-supervised learning accuracy.
method Particle competition and cooperation algorithm for robust semi-supervised learning.
result Improved robustness to label noise compared to existing methods.

Paper proposes an algorithm to recover full supervision from weakly labeled data.

problem Machine learning requires expensive data annotation, motivating the use of weak supervision.
method The paper introduces a disambiguation principle and an empirical disambiguation algorithm for partial labelling.
result The algorithm achieves exponential convergence rates under learnability assumptions.

Paper introduces a semi-supervised method for image segmentation using a small set of labeled images.

problem Costly and time-consuming to create large labeled datasets for semantic segmentation.
method Uses a small set of fully labeled images and a weak set of only bounding box labeled images. Trains a primary model with an ancillary model generating initial labels and a self-correction module improving these labels.
result Models trained with a small fully supervised set perform similarly or better than those trained with a large fully supervised set, requiring significantly less annotation effort.

Dugong models multi-resolution weak supervision for sequential data.

problem Estimating unknown accuracies and correlations of weak supervision sources for sequential data.
method Dugong, a framework that models multi-resolution weak supervision sources with complex correlations, using parameter sharing to improve sample complexity.
result Dugong outperforms traditional supervision by 36.8 F1 points on clinician-validated labels for biomedical video repositories.

Doubly robust self-training improves semi-supervised learning by balancing labeled and pseudo-labeled data.

problem Improving semi-supervised learning performance with limited labeled data.
method Introduces doubly robust self-training, a method that combines labeled and pseudo-labeled data to balance between labeled-only and pseudo-labeled-only training.
result Demonstrates superior performance of doubly robust self-training on ImageNet and nuScenes datasets.

Poisson learning improves graph-based semi-supervised learning at very low label rates.

problem Degeneracy of Laplacian semi-supervised learning at low label rates.
method Replaces label assignment with source and sink placement, solving Poisson equation.
result Provably more stable and informative predictions than Laplacian learning.