Training deep neural networks (DNNs) with noisy labels is a challenging problem due to over-parameterization. DNNs tend to essentially fit on clean samples at a higher rate in the initial stages, and later fit on the noisy samples at a relatively lower rate. Thus, with a noisy dataset, the test accuracy increases initially and drops in the later stages. To find an early stopping point at the maximum obtainable test accuracy (MOTA), recent studies assume either that i) a clean validation set is available or ii) the noise ratio is known, or, both. However, often a clean validation set is unavailable, and the noise estimation can be inaccurate. To overcome these issues, we provide a novel training solution, free of these conditions. We analyze the rate of change of the training accuracy for different noise ratios under different conditions to identify a training stop region. We further develop a heuristic algorithm based on a small-learning assumption to find a training stop point (TSP) at or close to MOTA. To the best of our knowledge, our method is the first to rely solely on the \textit{training behavior}, while utilizing the entire training set, to automatically find a TSP. We validated the robustness of our algorithm (AutoTSP) through several experiments on CIFAR-10, CIFAR-100, and a real-world noisy dataset for different noise ratios, noise types, and architectures.
Annotation of training data is the major bottleneck in the creation of text classification systems. Active learning is a commonly used technique to reduce the amount of training data one needs to label. A crucial aspect of active learning is determining when to stop labeling data. Three potential sources for informing when to stop active learning are an additional labeled set of data, an unlabeled set of data, and the training data that is labeled during the process of active learning. To date, no one has compared and contrasted the advantages and disadvantages of stopping methods based on the…
University of Sydney（悉尼大学）；Xidian University（西安电子科技大学）；RIKEN（理化学研究所）；Hong Kong Baptist University（香港浸会大学）；The University of Melbourne（墨尔本大学）；Brain-Inspired Technology Co., Ltd.（脑启发科技有限公司）
A similarity label indicates whether two instances belong to the same class while a class label shows the class of the instance. Without class labels, a multi-class classifier could be learned from similarity-labeled pairwise data by meta classification learning. However, since the similarity label is less informative than the class label, it is more likely to be noisy. Deep neural networks can easily remember noisy data, leading to overfitting in classification. In this paper, we propose a method for learning from only noisy-similarity-labeled data. Specifically, to model the noise, we employ…
Graduate School of Knowledge Service Engineering（知识服务工程研究生院）
Noisy labels are very common in real-world training data, which lead to poor generalization on test data because of overfitting to the noisy labels. In this paper, we claim that such overfitting can be avoided by "early stopping" training a deep neural network before the noisy labels are severely memorized. Then, we resume training the early stopped network using a "maximal safe set," which maintains a collection of almost certainly true-labeled samples at each epoch since the early stop point. Putting them all together, our novel two-phase training method, called Prestopping, realizes noise-f…
This paper studies early-stopped mirror descent applied to noisy sparse phase retrieval, which is the problem of recovering a $k$-sparse signal $\mathbf{x}^\star\in\mathbb{R}^n$ from a set of quadratic Gaussian measurements corrupted by sub-exponential noise. We consider the (non-convex) unregularized empirical risk minimization problem and show that early-stopped mirror descent, when equipped with the hyperbolic entropy mirror map and proper initialization, achieves a nearly minimax-optimal rate of convergence, provided the sample size is at least of order $k^2$ (modulo logarithmic term) and …
School of Electronic Information and Communications（电子信息与通信学院）；Huazhong University of Science and Technology（华中科技大学）
Label noise may affect the generalization of classifiers, and the effective learning of main patterns from samples with noisy labels is an important challenge. Recent studies have shown that deep neural networks tend to prioritize the learning of simple patterns over the memorization of noise patterns. This suggests a possible method to search for the best generalization that learns the main pattern until the noise begins to be memorized. Traditional approaches often employ a clean validation set to find the best stop timing of learning, i.e., early stopping. However, the generalization perfor…
University of Sydney（悉尼大学）；Xidian University（西安电子科技大学）；Hong Kong Baptist University（香港浸会大学）；Meituan-Dianping Group（美团点评集团）；RIKEN AIP（理化学研究所革新智能综合研究中心）
The memorization effect of deep neural network (DNN) plays a pivotal role in many state-of-the-art label-noise learning methods. To exploit this property, the early stopping trick, which stops the optimization at the early stage of training, is usually adopted. Current methods generally decide the early stopping point by considering a DNN as a whole. However, a DNN can be considered as a composition of a series of layers, and we find that the latter layers in a DNN are much more sensitive to label noise, while their former counterparts are quite robust. Therefore, selecting a stopping point fo…
National University of Singapore（新加坡国立大学）；University of Minnesota（明尼苏达大学）
Despite the success of deep neural networks (DNNs) in image classification tasks, the human-level performance relies on massive training data with high-quality manual annotations, which are expensive and time-consuming to collect. There exist many inexpensive data sources on the web, but they tend to contain inaccurate labels. Training on noisy labeled datasets causes performance degradation because DNNs can easily overfit to the label noise. To overcome this problem, we propose a noise-tolerant training algorithm, where a meta-learning update is performed prior to conventional gradient update…
Data61, CSIRO（联邦科学与工业研究组织Data61）；The University of Sydney（悉尼大学）；NYU Center for Data Science（纽约大学数据科学中心）
Convolutional Neural Networks (CNNs) have demonstrated superiority in learning patterns, but are sensitive to label noises and may overfit noisy labels during training. The early stopping strategy averts updating CNNs during the early training phase and is widely employed in the presence of noisy labels. Motivated by biological findings that the amplitude spectrum (AS) and phase spectrum (PS) in the frequency domain play different roles in the animal's vision system, we observe that PS, which captures more semantic information, can increase the robustness of DNNs to label noise, more so than A…
The Pennsylvania State University（宾夕法尼亚州立大学）；Michigan State University（密歇根州立大学）
Graph Neural Networks (GNNs) have shown their great ability in modeling graph structured data. However, real-world graphs usually contain structure noises and have limited labeled nodes. The performance of GNNs would drop significantly when trained on such graphs, which hinders the adoption of GNNs on many applications. Thus, it is important to develop noise-resistant GNNs with limited labeled nodes. However, the work on this is rather limited. Therefore, we study a novel problem of developing robust GNNs on noisy graphs with limited labeled nodes. Our analysis shows that both the noisy edges …
University of Tokyo（东京大学）；NTT Communication Science Laboratories（NTT通信科学实验室）
Positive-unlabeled learning refers to the process of training a binary classifier using only positive and unlabeled data. Although unlabeled data can contain positive data, all unlabeled data are regarded as negative data in existing positive-unlabeled learning methods, which resulting in diminishing performance. We provide a new perspective on this problem -- considering unlabeled data as noisy-labeled data, and introducing a new formulation of PU learning as a problem of joint optimization of noisy-labeled data. This research presents a methodology that assigns initial pseudo-labels to unlab…
UiT The Arctic University of Norway（挪威北极大学）；Universidad Rey Juan Carlos（胡安·卡洛斯国王大学）
Noisy labeled data represent a rich source of information that often are easily accessible and cheap to obtain, but label noise might also have many negative consequences if not accounted for. How to fully utilize noisy labels has been studied extensively within the framework of standard supervised machine learning over a period of several decades. However, very little research has been conducted on solving the challenge posed by noisy labels in non-standard settings. This includes situations where only a fraction of the samples are labeled (semi-supervised) and each high-dimensional sample is…
TU Delft（代尔夫特理工大学）；Université Grenoble Alpes（格勒诺布尔阿尔卑斯大学）；ABB Future Labs（ABB未来实验室）
Noisy labeled data is more a norm than a rarity for self-generated content that is continuously published on the web and social media. Due to privacy concerns and governmental regulations, such a data stream can only be stored and used for learning purposes in a limited duration. To overcome the noise in this on-line scenario we propose QActor which novel combines: the selection of supposedly clean samples via quality models and actively querying an oracle for the most informative true labels. While the former can suffer from low data volumes of on-line scenarios, the latter is constrained by …
University of Pennsylvania（宾夕法尼亚大学）；The University of Tokyo（东京大学）；RIKEN Center for Advanced Intelligence Project（理化学研究所先进智能项目中心）
With the widespread use of machine learning for classification, it becomes increasingly important to be able to use weaker kinds of supervision for tasks in which it is hard to obtain standard labeled data. One such kind of supervision is provided pairwise---in the form of Similar (S) pairs (if two examples belong to the same class) and Dissimilar (D) pairs (if two examples belong to different classes). This kind of supervision is realistic in privacy-sensitive domains. Although this problem has been looked at recently, it is unclear how to learn from such supervision under label noise, which …
The remarkable success of today's deep neural networks highly depends on a massive number of correctly labeled data. However, it is rather costly to obtain high-quality human-labeled data, leading to the active research area of training models robust to noisy labels. To achieve this goal, on the one hand, many papers have been dedicated to differentiating noisy labels from clean ones to increase the generalization of DNN. On the other hand, the increasingly prevalent methods of self-semi-supervised learning have been proven to benefit the tasks when labels are incomplete. By 'semi' we regard t…
Google Research（谷歌研究院）；Carnegie Mellon University（卡内基梅隆大学）
We present Noisy Student Training, a semi-supervised learning approach that works well even when labeled data is abundant. Noisy Student Training achieves 88.4% top-1 accuracy on ImageNet, which is 2.0% better than the state-of-the-art model that requires 3.5B weakly labeled Instagram images. On robustness test sets, it improves ImageNet-A top-1 accuracy from 61.0% to 83.7%, reduces ImageNet-C mean corruption error from 45.7 to 28.3, and reduces ImageNet-P mean flip rate from 27.8 to 12.2. Noisy Student Training extends the idea of self-training and distillation with the use of equal-or-larger…
Sungsin Women’s University（诚信女子大学）；Seoul National University（首尔大学）
In many classification problems, collecting massive clean-annotated data is not easy, and thus a lot of researches have been done to handle data with noisy labels. Most recent state-of-art solutions for noisy label problems are built on the small-loss strategy which exploits the memorization effect. While it is a powerful tool, the memorization effect has several drawbacks. The performances are sensitive to the choice of a training epoch required for utilizing the memorization effect. In addition, when the labels are heavily contaminated or imbalanced, the memorization effect may not occur in …
Pohang University of Science and Technology（浦项科技大学）；Seoul National University of Science and Technology (SeoulTech)（首尔国立科技大学（首尔科技大学））
Because deep learning is vulnerable to noisy labels, sample selection techniques, which train networks with only clean labeled data, have attracted a great attention. However, if the labels are dominantly corrupted by few classes, these noisy samples are called dominant-noisy-labeled samples, the network also learns dominant-noisy-labeled samples rapidly via content-aware optimization. In this study, we propose a compelling criteria to penalize dominant-noisy-labeled samples intensively through class-wise penalty labels. By averaging prediction confidences for the each observed label, we obtai…
Deep neural networks (DNNs) suffer from noisy-labeled data because of the risk of overfitting. To avoid the risk, in this paper, we propose a novel DNN training method with sample selection based on adaptive k-set selection, which selects k (< n) clean sample candidates from the whole n noisy training samples at each epoch. It has a strong advantage of guaranteeing the performance of the selection theoretically. Roughly speaking, a regret, which is defined by the difference between the actual selection and the best selection, of the proposed method is theoretically bounded, even though the bes…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Amazon Web Services（亚马逊云科技）
Supervised learning depends on annotated examples, which are taken to be the \emph{ground truth}. But these labels often come from noisy crowdsourcing platforms, like Amazon Mechanical Turk. Practitioners typically collect multiple labels per example and aggregate the results to mitigate noise (the classic crowdsourcing problem). Given a fixed annotation budget and unlimited unlabeled data, redundant annotation comes at the expense of fewer labeled examples. This raises two fundamental questions: (1) How can we best learn from noisy workers? (2) How should we allocate our labeling budget to ma…
The Pennsylvania State University（宾夕法尼亚州立大学）；IBM（国际商业机器公司）
Graph Neural Networks (GNNs) have achieved promising results for semi-supervised learning tasks on graphs such as node classification. Despite the great success of GNNs, many real-world graphs are often sparsely and noisily labeled, which could significantly degrade the performance of GNNs, as the noisy information could propagate to unlabeled nodes via graph structure. Thus, it is important to develop a label noise-resistant GNN for semi-supervised node classification. Though extensive studies have been conducted to learn neural networks with noisy labels, they mostly focus on independent and…
Music Technology Group, Universitat Pompeu Fabra（庞培法布拉大学音乐技术组）；Google, Inc.（谷歌公司）
This paper introduces Task 2 of the DCASE2019 Challenge, titled "Audio tagging with noisy labels and minimal supervision". This task was hosted on the Kaggle platform as "Freesound Audio Tagging 2019". The task evaluates systems for multi-label audio tagging using a large set of noisy-labeled data, and a much smaller set of manually-labeled data, under a large vocabulary setting of 80 everyday sound classes. In addition, the proposed dataset poses an acoustic mismatch problem between the noisy train set and the test set due to the fact that they come from different web audio sources. This can …
Manually labeled corpora are expensive to create and often not available for low-resource languages or domains. Automatic labeling approaches are an alternative way to obtain labeled data in a quicker and cheaper way. However, these labels often contain more errors which can deteriorate a classifier's performance when trained on this data. We propose a noise layer that is added to a neural network architecture. This allows modeling the noise and train on a combination of clean and noisy data. We show that in a low-resource NER task we can improve performance by up to 35% by using additional, n…
Department of Electronic Engineering, Tsinghua University, Beijing, China（中国北京清华大学电子工程系）；Institute for Precision Medicine, Tsinghua University, Beijing, China（中国北京清华大学精准医学研究院）
Deep learning methods have achieved promising performance in many areas, but they are still struggling with noisy-labeled images during the training process. Considering that the annotation quality indispensably relies on great expertise, the problem is even more crucial in the medical image domain. How to eliminate the disturbance from noisy labels for segmentation tasks without further annotations is still a significant challenge. In this paper, we introduce our label quality evaluation strategy for deep neural networks automatically assessing the quality of each label, which is not explicit…
National University of Defense Technology（国防科技大学）；University of Surrey（萨里大学）
High quality labeled datasets have allowed deep learning to achieve impressive results on many sound analysis tasks. Yet, it is labor-intensive to accurately annotate large amount of audio data, and the dataset may contain noisy labels in the practical settings. Meanwhile, the deep neural networks are susceptive to those incorrect labeled data because of their outstanding memorization ability. In this paper, we present a novel framework, named CrossFilter, to combat the noisy labels problem for audio tagging. Multiple representations (such as, Logmel and MFCC) are used as the input of our fram…
Optimization plays a key role in the training of deep neural networks. Deciding when to stop training can have a substantial impact on the performance of the network during inference. Under certain conditions, the generalization error can display a double descent pattern during training: the learning curve is non-monotonic and seemingly diverges before converging again after additional epochs. This optimization pattern can lead to early stopping procedures to stop training before the second convergence and consequently select a suboptimal set of parameters for the network, with worse performan…
Beijing University of Posts and Telecommunications（北京邮电大学）；Beijing University Of Technology（北京工业大学）；Peking University（北京大学）
Imperfect labels are ubiquitous in real-world datasets and seriously harm the model performance. Several recent effective methods for handling noisy labels have two key steps: 1) dividing samples into cleanly labeled and wrongly labeled sets by training loss, 2) using semi-supervised methods to generate pseudo-labels for samples in the wrongly labeled set. However, current methods always hurt the informative hard samples due to the similar loss distribution between the hard samples and the noisy ones. In this paper, we proposed PGDF (Prior Guided Denoising Framework), a novel framework to lear…
Recently deep neural networks have shown their capacity to memorize training data, even with noisy labels, which hurts generalization performance. To mitigate this issue, we provide a simple but effective baseline method that is robust to noisy labels, even with severe noise. Our objective involves a variance regularization term that implicitly penalizes the Jacobian norm of the neural network on the whole training set (including the noisy-labeled data), which encourages generalization and prevents overfitting to the corrupted labels. Experiments on both synthetically generated incorrect label…
Active learning is an increasingly important branch of machine learning and a powerful technique for natural language processing. The main advantage of active learning is its potential to reduce the amount of labeled data needed to learn high-performing models. A vital aspect of an effective active learning algorithm is the determination of when to stop obtaining additional labeled data. Several leading state-of-the-art stopping methods use a stop set to help make this decision. However, there has been relatively less attention given to the choice of stop set than to the stopping algorithms th…
We propose self-training with noisy student-teacher approach for streaming keyword spotting, that can utilize large-scale unlabeled data and aggressive data augmentation. The proposed method applies aggressive data augmentation (spectral augmentation) on the input of both student and teacher and utilize unlabeled data at scale, which significantly boosts the accuracy of student against challenging conditions. Such aggressive augmentation usually degrades model performance when used with supervised training with hard-labeled data. Experiments show that aggressive spec augmentation on baseline s…
Department of Physics & Institute for Physics of Intelligence, University of Tokyo（东京大学物理与智能物理研究所）
Learning in the presence of label noise is a challenging yet important task: it is crucial to design models that are robust in the presence of mislabeled datasets. In this paper, we discover that a new class of loss functions called the gambler's loss provides strong robustness to label noise across various levels of corruption. We show that training with this loss function encourages the model to "abstain" from learning on the data points with noisy labels, resulting in a simple and effective method to improve robustness and generalization. In addition, we propose two practical extensions of …
Noisy labels are very common in deep supervised learning. Although many studies tend to improve the robustness of deep training for noisy labels, rare works focus on theoretically explaining the training behaviors of learning with noisily labeled data, which is a fundamental principle in understanding its generalization. In this draft, we study its two phenomena, clean data first and phase transition, by explaining them from a theoretical viewpoint. Specifically, we first show that in the first epoch training, the examples with clean labels will be learned first. We then show that after the le…
In this paper, we address the problem of effectively self-training neural networks in a low-resource setting. Self-training is frequently used to automatically increase the amount of training data. However, in a low-resource scenario, it is less effective due to unreliable annotations created using self-labeling of unlabeled data. We propose to combine self-training with noise handling on the self-labeled data. Directly estimating noise on the combined clean training set and self-labeled data can lead to corruption of the clean data and hence, performs worse. Thus, we propose the Clean and Noi…
A common approach in positive-unlabeled learning is to train a classification model between labeled and unlabeled data. This strategy is in fact known to give an optimal classifier under mild conditions; however, it results in biased empirical estimates of the classifier performance. In this work, we show that the typically used performance measures such as the receiver operating characteristic curve, or the precision-recall curve obtained on such data can be corrected with the knowledge of class priors; i.e., the proportions of the positive and negative examples in the unlabeled data. We exte…
Michigan State University（密歇根州立大学）；Zhejiang University（浙江大学）；Yahoo Labs!（雅虎实验室）
We study the problem of multiple kernel learning from noisy labels. This is in contrast to most of the previous studies on multiple kernel learning that mainly focus on developing efficient algorithms and assume perfectly labeled training examples. Directly applying the existing multiple kernel learning algorithms to noisily labeled examples often leads to suboptimal performance due to the incorrect class assignments. We address this challenge by casting multiple kernel learning from noisy labels into a stochastic programming problem, and presenting a minimax formulation. We develop an efficie…
Drexel University（德雷塞尔大学）；Microsoft Research Asia, China（微软亚洲研究院(中国)）
Recently deep neural networks have been successfully used for various classification tasks, especially for problems with massive perfectly labeled training data. However, it is often costly to have large-scale credible labels in real-world applications. One solution is to make supervised learning robust with imperfectly labeled input. In this paper, we develop a distribution correction approach that allows deep neural networks to avoid overfitting imperfect training data. Specifically, we treat the noisy input as samples from an incorrect distribution, which will be automatically corrected dur…
Learning video concept detectors automatically from the big but noisy web data with no additional manual annotations is a novel but challenging area in the multimedia and the machine learning community. A considerable amount of videos on the web are associated with rich but noisy contextual information, such as the title, which provides weak annotations or labels about the video content. To leverage the big noisy web labels, this paper proposes a novel method called WEbly-Labeled Learning (WELL), which is established on the state-of-the-art machine learning algorithm inspired by the learning p…
IBM India Research Lab（IBM印度研究院）；Yahoo! Labs（雅虎实验室）；Dept. of CSA, IISc（印度科学理工学院计算机科学与自动化系）
We consider the problem of Probably Approximate Correct (PAC) learning of a binary classifier from noisy labeled examples acquired from multiple annotators (each characterized by a respective classification noise rate). First, we consider the complete information scenario, where the learner knows the noise rates of all the annotators. For this scenario, we derive sample complexity bound for the Minimum Disagreement Algorithm (MDA) on the number of labeled examples to be obtained from each annotator. Next, we consider the incomplete information scenario, where each annotator is strategic and ho…
Clova AI Research, NAVER Corp.（NAVER公司Clova人工智能研究院）；Search Solution Inc.（搜索解决方案公司）；Seoul National University（首尔大学）
The cost of annotating transcriptions for large speech corpora becomes a bottleneck to maximally enjoy the potential capacity of deep neural network-based automatic speech recognition models. In this paper, we present a new training pipeline boosting the conventional active learning approach targeting label-efficient learning to resolve the mentioned problem. Existing active learning methods only focus on selecting a set of informative samples under a labeling budget. One step further, we suggest that the training efficiency can be further improved by utilizing the unlabeled samples, exceeding…
University of Technology Sydney（悉尼科技大学）；RIKEN（理化学研究所）；Hong Kong Baptist University（香港浸会大学）；University of Tokyo（东京大学）
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, more realistic and more challenging problem setting, where classifiers have to be trained with noisy labeled data from SD and unlabeled data from TD -- we name it wildly UDA (WUDA). We show that WUDA ruins all UDA methods if taking no care of label noise in SD, and to this end,…
Gwangju Institute of Science and Technology（光州科学技术院）
This report proposes a polyphonic sound event detection (SED) method for the DCASE 2021 Challenge Task 4. The proposed SED model consists of two stages: a mean-teacher model for providing target labels regarding weakly labeled or unlabeled data and a self-training-based noisy student model for predicting strong labels for sound events. The mean-teacher model, which is based on the residual convolutional recurrent neural network (RCRNN) for the teacher and student model, is first trained using all the training data from a weakly labeled dataset, an unlabeled dataset, and a strongly labeled synt…
As sound event classification moves towards larger datasets, issues of label noise become inevitable. Web sites can supply large volumes of user-contributed audio and metadata, but inferring labels from this metadata introduces errors due to unreliable inputs, and limitations in the mapping. There is, however, little research into the impact of these errors. To foster the investigation of label noise in sound event classification we present FSDnoisy18k, a dataset containing 42.5 hours of audio across 20 sound classes, including a small amount of manually-labeled data and a larger quantity of r…
The models of n-ary cross sentence relation extraction based on distant supervision assume that consecutive sentences mentioning n entities describe the relation of these n entities. However, on one hand, this assumption introduces noisy labeled data and harms the models' performance. On the other hand, some non-consecutive sentences also describe one relation and these sentences cannot be labeled under this assumption. In this paper, we relax this strong assumption by a weaker distant supervision assumption to address the second issue and propose a novel sentence distribution estimator model …
Deep neural networks (DNNs) exhibit great success on many tasks with the help of large-scale well annotated datasets. However, labeling large-scale data can be very costly and error-prone so that it is difficult to guarantee the annotation quality (i.e., having noisy labels). Training on these noisy labeled datasets may adversely deteriorate their generalization performance. Existing methods either rely on complex training stage division or bring too much computation for marginal performance improvement. In this paper, we propose a Temporal Calibrated Regularization (TCR), in which we utilize …
Deep neural networks (DNNs) trained on large-scale datasets have exhibited significant performance in image classification. Many large-scale datasets are collected from websites, however they tend to contain inaccurate labels that are termed as noisy labels. Training on such noisy labeled datasets causes performance degradation because DNNs easily overfit to noisy labels. To overcome this problem, we propose a joint optimization framework of learning DNN parameters and estimating true labels. Our framework can correct labels during training by alternating update of network parameters and label…
The classification of electrocardiographic (ECG) signals is a challenging problem for healthcare industry. Traditional supervised learning methods require a large number of labeled data which is usually expensive and difficult to obtain for ECG signals. Active learning is well-suited for ECG signal classification as it aims at selecting the best set of labeled data in order to maximize the classification performance. Motivated by the fact that ECG data are usually heavily unbalanced among different classes and the class labels are noisy as they are manually labeled, this paper proposes a novel…
