arXiv research

Deep networks can handle noisy labels up to a certain threshold.

TrustNet robustly learns noise patterns from trusted data to improve weakly-supervised classification.

We study the robustness to symmetric label noise of GNNs training procedures. By combining the nonlinear neural message-passing models (e.g. Graph Isomorphism Networks, GraphSAGE, etc.) with loss correction methods, we present a noise-tolerant approach for the graph classification task. Our experiments show that test a…

Label smoothing improves model performance even with noisy labels.

Symmetrizes loss functions to improve neural network robustness against noisy labels.

Training accurate deep neural networks (DNNs) in the presence of noisy labels is an important and challenging task. Though a number of approaches have been proposed for learning with noisy labels, many open issues remain. In this paper, we show that DNN learning with Cross Entropy (CE) exhibits overfitting to noisy lab…

Study explores loss design for decision trees to improve robustness against noisy labels.

New insights on robust learning under strong noise models.

Noisy labels are ubiquitous in real-world datasets, which poses a challenge for robustly training deep neural networks (DNNs) as DNNs usually have the high capacity to memorize the noisy labels. In this paper, we find that the test accuracy can be quantitatively characterized in terms of the noise ratio in datasets. In…

ANTIDOTE reduces noisy labels influence during learning.

In binary classification framework, we are interested in making cost sensitive label predictions in the presence of uniform/symmetric label noise. We first observe that $0$-$1$ Bayes classifiers are not (uniform) noise robust in cost sensitive setting. To circumvent this impossibility result, we present two schemes; un…

Deep neural networks (DNNs) have been shown to over-fit a dataset when being trained with noisy labels for a long enough time. To overcome this problem, we present a simple and effective method self-ensemble label filtering (SELF) to progressively filter out the wrong labels during training. Our method improves the tas…

New methods for handling time-varying label noise in time series classification.

Interpolating label noise makes models vulnerable to adversarial attacks.

Proposes a new model for noisy labels considering multiple labelers and adversarial attacks.

Proposes a progressive label correction method for feature-dependent label noise.

Inserting label noise can improve model accuracy and fairness.

Paper tackles robust imitation learning from noisy demonstrations.

NoiseRank reduces label noise without supervision, improving classification accuracy.

Label noise in adversarial training leads to robust overfitting, explained and mitigated.

Nonlinear SGD achieves high-probability rates in non-convex optimization with heavy-tailed noise.

The study analyzes how label noise affects deep learning feature learning.

A new method handles label noise by leveraging causal information.

Study on noise models for noisy labels in NLP.

A method uses confidence scores to handle noisy labels for each instance.

Proposes MGPLL for PL learning with non-random noise.

Because large, human-annotated datasets suffer from labeling errors, it is crucial to be able to train deep neural networks in the presence of label noise. While training image classification models with label noise have received much attention, training text classification models have not. In this paper, we propose an…

BeGIN benchmarks GNNs for instance-dependent label noise in graphs.

The paper cleans label noise in supervised classification using Bernoulli sampling.

Paper tackles instance-dependent label noise by approximating it with part-dependent noise.

In many applications of classifier learning, training data suffers from label noise. Deep networks are learned using huge training data where the problem of noisy labels is particularly relevant. The current techniques proposed for learning deep networks under label noise focus on modifying the network architecture and…

Collecting large-scale data with clean labels for supervised training of neural networks is practically challenging. Although noisy labels are usually cheap to acquire, existing methods suffer a lot from label noise. This paper targets at the challenge of robust training at high label noise regimes. The key insight to …

Paper improves image classification accuracy with a new Noise Modeling Network.

Boosting is known to be sensitive to label noise. We studied two approaches to improve AdaBoost's robustness against labelling errors. One is to employ a label-noise robust classifier as a base learner, while the other is to modify the AdaBoost algorithm to be more robust. Empirical evaluation shows that a committee of…

We introduce a novel method to combat label noise when training deep neural networks for classification. We propose a loss function that permits abstention during training thereby allowing the DNN to abstain on confusing samples while continuing to learn and improve classification performance on the non-abstained sampl…

Paper proposes a universal probabilistic model for handling instance-dependent label noise.

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

This paper studies how label noise affects Federated Learning.

This paper identifies and estimates the label noise transition matrix without ground truth labels.

Paper presents robust boosting methods for label noise.

Study robustness of conformal prediction to label noise in regression and classification.

The real-world data is often susceptible to label noise, which might constrict the effectiveness of the existing state of the art algorithms for ordinal regression. Existing works on ordinal regression do not take label noise into account. We propose a theoretically grounded approach for class conditional label noise i…

Bayes classifier cannot be learned from noisy labels without knowing noise distribution.

Study enhances classifier robustness against noisy labels.

S-SGD adds symmetrical noise to weights to avoid sharp minima in deep learning.

Logistic regression can handle noisy labels effectively when labels are imperfectly assigned by multiple experts.

Performing controlled experiments on noisy data is essential in understanding deep learning across noise levels. Due to the lack of suitable datasets, previous research has only examined deep learning on controlled synthetic label noise, and real-world label noise has never been studied in a controlled setting. This pa…

Study real-world noisy labels from human annotations for better understanding.