Neural networks learn clean data patterns first, then noisy data, leading to improved performance initially but deteriorating later.
problem Improvement in prediction error on clean data during early training of neural networks with noisy labels.
method Theoretical analysis and experiments to explore the dynamics of gradient descent and the impact of clean and noisy data.
result Neural networks prioritize learning clean data patterns first, leading to improved performance initially but deteriorating later due to diminishing gradient dominance of clean samples over noisy ones.
PClean automates Bayesian data cleaning for specific datasets.
problem Bayesian inference for diverse and complex data cleaning.
method Domain-specific probabilistic programming language with custom models and inference.
result PClean programs outperform general-purpose PPLs in accuracy and runtime.
INN method refines clean labeled data from noisy labels.
problem Handling noisy labels in deep neural networks.
method INN method based on memorization effect at neighbor regions.
result INN method resolves memorization effect shortcomings.
R package tsrobprep cleans and prepares time series data robustly.
problem Inefficient methods for handling missing values and outliers in time series data.
method Model-based methods for imputation and outlier detection considering time series properties.
result Robust and tunable methods for data preprocessing in time series analysis.
We apply basic statistical reasoning to signal reconstruction by machine learning -- learning to map corrupted observations to clean signals -- with a simple and powerful conclusion: it is possible to learn to restore images by only looking at corrupted examples, at performance at and sometimes exceeding training using…
Adversarial training leads to clean data generalization with significant robust overfitting gap.
problem Significant robust generalization gap in adversarial training.
method Two theoretical views: representation complexity and training dynamics.
result ReLU nets with O(ND) extra parameters can achieve CGRO. This paper presents a statistical method of single-channel speech enhancement that uses a variational autoencoder (VAE) as a prior distribution on clean speech. A standard approach to speech enhancement is to train a deep neural network (DNN) to take noisy speech as input and output clean speech. Although this supervis…
Study improves resilience against adversarial clean-label attacks in real and noisy settings.
problem Ensuring accurate predictions in the presence of adversarial clean-label samples.
method Sequential learning from a stream of i.i.d. data, allowing abstention for uncertain predictions.
result Theoretical analysis and adaptations for the agnostic setting with a clean-label adversary and noise.
Self-supervised method predicts clean signal and noise distribution from noisy images.
problem Blind denoising and noise estimation in biomedical images with limited clean data.
method Two neural networks jointly predict clean signal and noise distribution from noisy observations.
result Significantly outperforms state-of-the-art algorithms on six biomedical image datasets.
SSMs can be poisoned with clean labels, leading to generalization failure.
problem The implicit bias of SSMs can be manipulated by including special training examples with clean labels.
method Formal proof and empirical demonstration of the phenomenon.
result SSMs can fail to generalize even with clean labels, due to the inclusion of special training examples.
Cincer cleans both new and past data by identifying and relabeling suspicious and counter-examples.
problem Sequential learning under label noise, especially in applications with human supervision.
method Cincer uses example-based explanations to identify and relabel suspicious and counter-examples, leveraging Fisher information matrix approximation.
result Cincer achieves better data and models by clarifying the model's suspicions, especially with FIM approximation.
A new method improves graph-based semi-supervised classification by removing noise and mixed signs.
problem Inaccurate soft labels and noise in graph-based semi-supervised classification.
method Triple-matrix-recovery-based robust auto-weighted label propagation framework (ALP-TMR).
result Improved robustness to noise and outliers in label estimation.
Enhances deep learning robustness to noise without sacrificing clean data accuracy.
problem Robustness of deep neural networks to input noise.
method Discriminative loss at penultimate layer and class-wise feature alignment with Gaussian noise.
result Improves robustness to various perturbations without degrading clean data accuracy.
The US Census Bureau corrupts data to protect privacy, but we show how to clean and analyze it effectively.
problem Analyzing Census data with intentional corruption to maintain privacy.
method Formulated a semiparametric model, proposed data cleaning, estimation, and inference procedures.
result Demonstrated that data cleaning can maintain precision and provided theoretical and empirical support.
New method generates clean data from corrupted observations.
problem Generating clean data from corrupted observations.
method Iterative update of a transport map using black-box corruption channel access.
result Converges to a self-consistent transport map that effectively inverts the corruption channel.
CLSVAE repairs systematic errors in images with minimal labeled data.
problem Repairing systematic errors in data, especially in images.
method CLSVAE models inliers as a smaller latent space representation, separating inlier and outlier patterns.
result CLSVAE achieves superior repairs with less than 2% labeled data, outperforming other methods.
Study proposes a clustering and logistic regression algorithm for PU classification under Non-SCAR.
problem PU classification under Non-SCAR condition when SCAR condition is unsatisfied.
method 2-means clustering followed by logistic regression.
result Efficacy of the proposed algorithm demonstrated on 11 real data sets and a synthetic set.
TS-Fault benchmarks TSF models against structural faults.
problem Evaluating the robustness of time series forecasting models against structured events.
method TS-Fault uses parameterized fault scenarios with controllable difficulty.
result Three findings contradict common leaderboard intuition.
New method improves false-/true-positive-rate estimation in fraud detection with noisy labels.
problem Estimating FPR/TPR in fraud detection with class-conditional label noise.
method Directly cleaning model's validation data to de-correlate cleaning error with model scores.
result Improves accuracy of FPR/TPR estimates, especially in asymmetric label noise scenarios.
Game theory helps machine learn better from adversarial queries.
problem Adversarial evasion in machine learning prediction.
method Repeated Bayesian Sequential Game to balance classifier selection and query type.
result Learner selects appropriate classifier for clean vs. adversarial queries.
Method cleans noisy training labels for biomedical data.
problem Accurately labeling biomedical data is challenging.
method Reliability-based training data cleaning with inductive conformal prediction.
result Significant enhancements in classification performance across multiple tasks.
Data quality issues have attracted widespread attention due to the negative impacts of dirty data on data mining and machine learning results. The relationship between data quality and the accuracy of results could be applied on the selection of the appropriate algorithm with the consideration of data quality and the d…
Paper proposes training deep nets on noisy labels without manual annotation.
problem Training deep neural networks on noisy labels without manual annotation.
method Directly train deep neural network on noisy candidate labels, early stopping to avoid overfitting.
result Training on noisy candidate labels yields higher test performance than on clean data.
MetaPoison poisons neural networks by learning to craft imperceptible changes to training data.
problem Data poisoning attacks on neural networks.
method MetaPoison uses meta-learning to approximate bilevel optimization for crafting poisons.
result MetaPoison outperforms previous methods and works in various scenarios.
The paper cleans label noise in supervised classification using Bernoulli sampling.
problem Label noise degrades supervised classifier performance.
method Proposes a label noise cleaning method based on Bernoulli random sampling.
result The method separates clean and noisy observations without prior label information.
Historical (Stressed-) Value-at-Risk ((S)VAR), and Expected Shortfall (ES), are widely used risk measures in regulatory capital and Initial Margin, i.e. funding, computations. However, whilst the definitions of VAR and ES are unambiguous, they depend on input distributions that are data-cleaning- and Data-Model-depende…
QActor optimizes learning from noisy labeled data streams by querying experts for clean labels.
problem Learning from noisy labeled data in continuous streams with limited oracle queries.
method Combines quality models for filtering and oracle queries for true labels, dynamically adjusting query limits.
result QActor nearly matches optimal accuracy with up to 6% additional ground truth data from experts.
EntProp increases entropy of clean samples to generate out-of-distribution data for better DNN performance.
problem Improving deep neural networks' accuracy and robustness to out-of-distribution data.
method High entropy propagation using data augmentation and free adversarial training.
result EntProp achieves higher standard accuracy and robustness with lower training cost.
Deep learning models are vulnerable to various adversarial manipulations of their training data, parameters, and input sample. In particular, an adversary can modify the training data and model parameters to embed backdoors into the model, so the model behaves according to the adversary's objective if the input contain…
In unsupervised domain adaptation (UDA), classifiers for the target domain (TD) are trained with clean labeled data from the source domain (SD) and unlabeled data from TD. However, in the wild, it is difficult to acquire a large amount of perfectly clean labeled data in SD given limited budget. Hence, we consider a new…
New method denoises and fills in missing image data without clean training data.
problem Denoising and inpainting images with noisy, incomplete data.
method Robust Hadamard Autoencoders trained on noisy, incomplete data.
result Autoencoders can perform denoising and inpainting simultaneously.
It is known that evaluating a certain approximation to the Jones polynomial for the plat closure of a braid is a BQP-complete problem. That is, this problem exactly captures the power of the quantum circuit model. The one clean qubit model is a model of quantum computation in which all but one qubit starts in the maxim…
PrIU optimizes machine learning model updates after data cleaning.
problem Incrementally updating machine learning models after removing problematic training samples.
method Provenance-based approach for efficient model parameter updates.
result PrIU-opt achieves up to two orders of magnitude speed-up compared to retraining from scratch.
Detects poisoned training samples in deep neural networks.
problem Data poisoning attacks on deep neural networks.
method Two approaches: parametric probability distributions and Bayesian deep neural networks.
result Uncertainty estimates from trained models can discriminate clean from poisoned samples.
When considering answering important questions with data, unsupervised data offers extensive insight opportunity and unique challenges. This study considers student survey data with a specific goal of clustering students into like groups with underlying concept of identifying different poverty levels. Fuzzy logic is co…
Neural networks are vulnerable to small adversarial perturbations. Existing literature largely focused on understanding and mitigating the vulnerability of learned models. In this paper, we demonstrate an intriguing phenomenon about the most popular robust training method in the literature, adversarial training: Advers…
A new algorithm reduces imbalanced data classification errors in multi-class settings.
problem Imbalanced data classification, especially with noise and overlapping classes.
method MC-CCR algorithm combining cleaning and resampling.
result High robustness to noise and superior performance compared to state-of-the-art methods.
Clean-label poisoning attacks inject innocuous looking (and "correctly" labeled) poison images into training data, causing a model to misclassify a targeted image after being trained on this data. We consider transferable poisoning attacks that succeed without access to the victim network's outputs, architecture, or (i…
Deploying machine learning systems in the real world requires both high accuracy on clean data and robustness to naturally occurring corruptions. While architectural advances have led to improved accuracy, building robust models remains challenging. Prior work has argued that there is an inherent trade-off between robu…
Paper cleans option price datasets by removing outliers.
problem Unusual option prices in datasets.
method Statistical techniques to identify and remove outliers.
result Removes option prices violating no arbitrage assumption.
Paper tackles label noise in large datasets, purifying noisy data with a nonparametric framework.
problem Label noise in large-scale datasets with coarse labels.
method Develops a model-agnostic nonparametric framework for classification.
result Framework purifies noisy data using a small clean dataset and manages ambiguous samples.
Defense against backdoor attacks by clustering incompatible data subsets.
problem Backdoor poisoning attacks on deep neural networks.
method Incompatibility clustering of data subsets during training.
result Successfully reduces attack success rate to below 1%.
Develops a robust training framework to detect backdoor attacks in DNNs.
problem Vulnerability of DNNs to backdoor attacks by poisoned training data.
method Collider framework selects prominent samples based on geometric structures and coreset selection objective.
result Significantly reduces backdoor success rate in various poisoned datasets.
Trimming helps in conformal prediction when it separates anomaly scores.
problem Effectiveness of trimming in conformal prediction under contamination.
method Analyse fixed-threshold trimming as a replacement of the contaminated calibration law with a retained law.
result Trimming helps when it separates anomaly scores, reducing clean-target coverage to a one-dimensional score-CDF transfer problem.
Graph neural networks (GNNs) are widely used in many applications. However, their robustness against adversarial attacks is criticized. Prior studies show that using unnoticeable modifications on graph topology or nodal features can significantly reduce the performances of GNNs. It is very challenging to design robust …
In this paper we are interested in the prediction of preterm birth based on diagnosis codes from longitudinal EHR. We formulate the prediction problem as a supervised classification with noisy labels. Our base classifier is a Recurrent Neural Network with an attention mechanism. We assume the availability of a data sub…
Study finds discrepancies in model explanations for clean vs. adversarial inputs.
problem Identifying adversarial attacks on neural networks.
method Utilized experimental results to propose a framework for detecting adversarial inputs.
result Proposed framework can identify adversarial inputs based on model explanations.
CAT improves robustness of neural networks by customizing perturbation levels.
problem Poor generalization of adversarial training on clean and perturbed data.
method CAT adapts perturbation level and label for each sample.
result CAT achieves better clean and robust accuracy than previous methods.