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.

168,695 papers · 148 categories

Trend · papers per month

64128191255 · Jun 202019922001200920172026
48 results for label distillation

Labels distilled from images improve model training efficiency and flexibility.

problem Creating synthetic labels for a small set of real images to train models effectively.
method Introduce a more robust and flexible meta-learning algorithm for distillation and an effective first-order strategy based on convex optimization layers.
result Label distillation leads to improved results and greater flexibility in neural architectures.

Dataset distillation is a method for reducing dataset sizes by learning a small number of synthetic samples containing all the information of a large dataset. This has several benefits like speeding up model training, reducing energy consumption, and reducing required storage space. Currently, each synthetic sample is …

2019-10-06abs ↗pdf ↗

This study improves knowledge distillation for RNN-T models with noisy labels.

problem Challenges in distilling knowledge from RNN-T models with variable quality teachers.
method Full-sum distillation and sequence-level knowledge distillation.
result Full-sum distillation outperforms other methods for RNN-T models, especially for bad teachers.

Self-distillation improves model performance by increasing teacher diversity and smoothing predictions.

problem Improving model generalization and performance through self-distillation.
method Interpreting self-distillation as MAP estimation and proposing instance-specific label smoothing.
result Self-distillation enhances model performance by increasing teacher diversity and smoothing predictions.

Instance- and Label-dependent label Noise (ILN) widely exists in real-world datasets but has been rarely studied. In this paper, we focus on Bounded Instance- and Label-dependent label Noise (BILN), a particular case of ILN where the label noise rates -- the probabilities that the true labels of examples flip into the …

2017-09-12abs ↗pdf ↗

Distillation works even with hard labels from overparameterized teacher, leading to better performance.

problem Improving model performance with hard labels from overparameterized teacher.
method Training a student model on a large held-out dataset labeled by a highly overparameterized teacher.
result Student model outperforms traditional approaches due to double descent phenomenon.

The paper analyzes knowledge distillation in wide neural networks, providing theoretical insights and practical implications.

problem Lack of theoretical understanding of knowledge distillation in wide neural networks.
method Theoretical analysis of knowledge distillation in a linearized model of a wide neural network, introducing a metric of task training difficulty.
result For a perfect teacher, a high ratio of teacher's soft labels can be beneficial. For imperfect teacher, hard labels can correct wrong predictions.

Rectified decision trees improve machine learning interpretability and effectiveness.

problem Combining interpretability and effectiveness in machine learning models.
method Knowledge distillation and modified decision tree splitting criteria.
result Soft labels improve model performance and reduce model size.

Self-distillation improves model performance in noisy label settings.

problem Improving model accuracy in supervised learning with noisy labels.
method Analyzes self-distillation in two supervised learning problems with noisy labels, using theoretical and empirical approaches.
result Optimal self-distillation parameter is greater than 1 in high label noise regimes, outperforming traditional methods.

Distillation is a method to transfer knowledge from one model to another and often achieves higher accuracy with the same capacity. In this paper, we aim to provide a theoretical understanding on what mainly helps with the distillation. Our answer is "early stopping". Assuming that the teacher network is overparameteri…

2019-10-02abs ↗pdf ↗

Label smoothing improves model performance even with noisy labels.

problem Mitigating label noise in deep learning models.
method Examined label smoothing as a technique to cope with label noise and compared it to loss-correction methods.
result Label smoothing is competitive with loss-correction techniques under label noise and beneficial for distillation from noisy data.

Proposes LsrKD and MrKD to improve neural network training performance.

problem Improving neural network training performance, especially on deep networks.
method Extends Label Smoothing Regularization with Self-Knowledge Distillation, introducing LsrKD and MrKD.
result LsrKD and MrKD significantly improve training performance on deep neural networks.

RKD improves clustering in semi-supervised learning with limited labels.

problem Improving clustering accuracy in semi-supervised learning with few labeled examples.
method RKD as spectral clustering on a teacher model's graph, with clustering error quantification.
result RKD provably leads to low clustering error in semi-supervised classification problems.

The ability of learning from noisy labels is very useful in many visual recognition tasks, as a vast amount of data with noisy labels are relatively easy to obtain. Traditionally, the label noises have been treated as statistical outliers, and approaches such as importance re-weighting and bootstrap have been proposed …

2017-03-07abs ↗pdf ↗

Deep Neural Networks (DNNs) are vulnerable to adversarial attacks, especially white-box targeted attacks. One scheme of learning attacks is to design a proper adversarial objective function that leads to the imperceptible perturbation for any test image (e.g., the Carlini-Wagner (C&W) method). Most methods address targ…

2019-05-25abs ↗pdf ↗

NURD improves model performance by distilling representations independent of nuisance variables.

problem Models trained under spurious correlations may fail on data with different nuisance-label relationships.
method Developed Nuisance-Randomized Distillation (NURD) to find representations independent of nuisance variables.
result NURD finds representations that perform better regardless of nuisance-label relationships.

Knowledge distillation improves model accuracy by mimicking teacher model probabilities.

problem Improving model accuracy through model compression.
method Casting knowledge distillation as a semiparametric inference problem, deriving new guarantees, and developing enhancements.
result Enhancements improve student performance by mitigating teacher overfitting and underfitting.

A framework learns dynamic soft labels to improve model generalization and accuracy.

problem Models trained on one-hot labels overfit and are sensitive to noisy annotations.
method Proposes a framework where labels are treated as learnable parameters, adapting dynamically during optimization.
result Consistent gains across different datasets and architectures, improving ResNet18 by 2.1% on CIFAR100.

Paper proposes a new method for training small models on regression problems.

problem Training small models for regression problems with noisy labels.
method Developed a new loss function and a multi-task network approach.
result Improved model accuracy on various datasets, consistent across different levels of annotation errors.

TL-ANDI distills context from source data to improve transfer learning for TFMs.

problem Limited transfer learning due to context-size constraints and distribution shifts.
method TL-ANDI uses posterior-aware distillation to construct a compact source context and locally distills labels.
result Improves transfer performance by addressing context-size and distribution shifts.

Study on ensemble, distillation, and self-distillation in deep learning models.

problem Improving test accuracy in deep learning models using ensemble and distillation methods.
method Formal study of ensemble and distillation, considering multi-view data structure.
result Proven that ensemble and distillation can improve test accuracy in deep learning models, and the superior performance can be distilled into a single model.

The generalization and learning speed of a multi-class neural network can often be significantly improved by using soft targets that are a weighted average of the hard targets and the uniform distribution over labels. Smoothing the labels in this way prevents the network from becoming over-confident and label smoothing…

2019-06-06abs ↗pdf ↗

SPEQ improves quantized neural networks by stochastic precision sharing and cosine similarity loss.

problem Improving quantized deep neural networks for edge devices.
method SPEQ combines stochastic precision sharing and cosine similarity loss for knowledge distillation.
result SPEQ outperforms existing methods in various tasks.

Distillation speeds up classifier training and provides insights into its success.

problem Empirical success of knowledge distillation without theoretical explanation.
method Study of linear and deep linear classifiers, proving a generalization bound.
result Three key factors for distillation success: data geometry, optimization bias, strong monotonicity.

Study shows optimal self-distillation improves model performance on noisy data.

problem Improving model performance on noisy Gaussian mixture data.
method Hyperparameter-tuned multi-stage self-distillation with a linear classifier, using replica method.
result Primary driver of SD's performance improvement is denoising through hard pseudo-labels.

A new distillation framework predicts stock trading volumes more accurately with less model size.

problem Predicting stock trading volumes using regression models without class correlations.
method Transformed regression model into a probabilistic forecasting model, matching distributions and correlational relationships.
result Framework achieves superior prediction accuracy with significantly smaller model size.

ExpertNet uses noisy labels to improve deep learning robustness.

problem Improving deep learning robustness against noisy labels.
method ExpertNet framework combining Amateur and Expert models, iteratively learning from noisy labels and images.
result ExpertNet achieves robust classification with as little as 20-50% training data, outperforming state-of-the-art models.

Knowledge Distillation (KD) is a model-agnostic technique to improve model quality while having a fixed capacity budget. It is a commonly used technique for model compression, where a larger capacity teacher model with better quality is used to train a more compact student model with better inference efficiency. Throug…

2020-02-10abs ↗pdf ↗

Sharp analysis of knowledge distillation for high-dimensional regression.

problem Characterizing the risk of target models in high-dimensional settings.
method Sharp non-asymptotic bounds for ridgeless regression under model and distribution shifts.
result Identifies optimal surrogate models and reveals benefits and limitations of discarding weak features.

A new method transfers adversarial robustness from teacher to student using feature distillation.

problem Adversarial robustness transfer across different models and tasks.
method Guided Adversarial Contrastive Distillation (GACD) with contrastive learning and sample reweighted estimation.
result GACD effectively transfers adversarial robustness from teacher to student, achieving comparable or better results.

Paper tackles adapting multiple domains to a target domain using distillation and dictionary learning.

problem Adapting multiple heterogeneous labeled source domains to an unlabeled target domain.
method Combines Multi-Source Domain Adaptation and Dataset Distillation with Dataset Dictionary Learning.
result Achieves state-of-the-art adaptation performance even with minimal labeled data.

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).