Real-world data often exhibits long-tailed distributions with heavy class imbalance, posing great challenges for deep recognition models. We identify a persisting dilemma on the value of labels in the context of imbalanced learning: on the one hand, supervision from labels typically leads to better results than its unsupervised counterparts; on the other hand, heavily imbalanced data naturally incurs "label bias" in the classifier, where the decision boundary can be drastically altered by the majority classes. In this work, we systematically investigate these two facets of labels. We demonstrate, theoretically and empirically, that class-imbalanced learning can significantly benefit in both semi-supervised and self-supervised manners. Specifically, we confirm that (1) positively, imbalanced labels are valuable: given more unlabeled data, the original labels can be leveraged with the extra data to reduce label bias in a semi-supervised manner, which greatly improves the final classifier; (2) negatively however, we argue that imbalanced labels are not useful always: classifiers that are first pre-trained in a self-supervised manner consistently outperform their corresponding baselines. Extensive experiments on large-scale imbalanced datasets verify our theoretically grounded strategies, showing superior performance over previous state-of-the-arts. Our intriguing findings highlight the need to rethink the usage of imbalanced labels in realistic long-tailed tasks. Code is available at https://github.com/YyzHarry/imbalanced-semi-self.
Semi-Supervised Learning (SSL) has achieved great success in overcoming the difficulties of labeling and making full use of unlabeled data. However, SSL has a limited assumption that the numbers of samples in different classes are balanced, and many SSL algorithms show lower performance for the datasets with the imbalanced class distribution. In this paper, we introduce a task of class-imbalanced semi-supervised learning (CISSL), which refers to semi-supervised learning with class-imbalanced data. In doing so, we consider class imbalance in both labeled and unlabeled sets. First, we analyze ex…
Stanford University（斯坦福大学）；Toyota Research Institute（丰田研究院）
Deep learning algorithms can fare poorly when the training dataset suffers from heavy class-imbalance but the testing criterion requires good generalization on less frequent classes. We design two novel methods to improve performance in such scenarios. First, we propose a theoretically-principled label-distribution-aware margin (LDAM) loss motivated by minimizing a margin-based generalization bound. This loss replaces the standard cross-entropy objective during training and can be applied with prior strategies for training with class-imbalance such as re-weighting or re-sampling. Second, we pr…
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）；Samsung Advanced Institute of Technology（三星综合技术院）；AItrics
While semi-supervised learning (SSL) has proven to be a promising way for leveraging unlabeled data when labeled data is scarce, the existing SSL algorithms typically assume that training class distributions are balanced. However, these SSL algorithms trained under imbalanced class distributions can severely suffer when generalizing to a balanced testing criterion, since they utilize biased pseudo-labels of unlabeled data toward majority classes. To alleviate this issue, we formulate a convex optimization problem to softly refine the pseudo-labels generated from the biased model, and develop a…
Multi-label classification (MLC) is an important class of machine learning problems that come with a wide spectrum of applications, each demanding a possibly different evaluation criterion. When solving the MLC problems, we generally expect the learning algorithm to take the hidden correlation of the labels into account to improve the prediction performance. Extracting the hidden correlation is generally a challenging task. In this work, we propose a novel deep learning framework to better extract the hidden correlation with the help of the memory structure within recurrent neural networks. Th…
Nanjing University（南京大学）；Tencent AI Lab（腾讯人工智能实验室）
Learning with Noisy Labels (LNL) has attracted significant attention from the research community. Many recent LNL methods rely on the assumption that clean samples tend to have "small loss". However, this assumption always fails to generalize to some real-world cases with imbalanced subpopulations, i.e., training subpopulations varying in sample size or recognition difficulty. Therefore, recent LNL methods face the risk of misclassifying those "informative" samples (e.g., hard samples or samples in the tail subpopulations) into noisy samples, leading to poor generalization performance. To addr…
FedReLa: Imbalanced Federated Learning via Re-Labeling
School of Computing and Information Systems, University of Melbourne, Victoria, Australia（墨尔本大学计算机与信息系统学院）；School of Statistics and Data Science, LPMC, KLMDASR, and LEBPS, Nankai University（南开大学统计与数据科学学院）；School of Mathematics and Statistics, University of Melbourne, Victoria, Australia（墨尔本大学数学与统计学学院）
Recent state-of-the-art methods in imbalanced semi-supervised learning (SSL) rely on confidence-based pseudo-labeling with consistency regularization. To obtain high-quality pseudo-labels, a high confidence threshold is typically adopted. However, it has been shown that softmax-based confidence scores in deep networks can be arbitrarily high for samples far from the training data, and thus, the pseudo-labels for even high-confidence unlabeled samples may still be unreliable. In this work, we present a new perspective of pseudo-labeling for imbalanced SSL. Without relying on model confidence, w…
Australian National University（澳大利亚国立大学）；Pohang University of Science and Technology（浦项科技大学）
Mutual information is widely applied to learn latent representations of observations, whilst its implication in classification neural networks remain to be better explained. We show that optimising the parameters of classification neural networks with softmax cross-entropy is equivalent to maximising the mutual information between inputs and labels under the balanced data assumption. Through experiments on synthetic and real datasets, we show that softmax cross-entropy can estimate mutual information approximately. When applied to image classification, this relation helps approximate the point…
Sun Yat-Sen University（中山大学）；Boston University（波士顿大学）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）
Unsupervised domain adaptation is a promising way to generalize deep models to novel domains. However, the current literature assumes that the label distribution is domain-invariant and only aligns the feature distributions or vice versa. In this work, we explore the more realistic task of Class-imbalanced Domain Adaptation: How to align feature distributions across domains while the label distributions of the two domains are also different? Taking a practical step towards this problem, we constructed the first benchmark with 22 cross-domain tasks from 6real-image datasets. We conducted compre…
Rutgers University - New Brunswick（罗格斯大学新布朗斯维克分校）；Weifang Medical University（潍坊医学院）
The paper presents Imbalance-XGBoost, a Python package that combines the powerful XGBoost software with weighted and focal losses to tackle binary label-imbalanced classification tasks. Though a small-scale program in terms of size, the package is, to the best of the authors' knowledge, the first of its kind which provides an integrated implementation for the two losses on XGBoost and brings a general-purpose extension on XGBoost for label-imbalanced scenarios. In this paper, the design and usage of the package are described with exemplar code listings, and its convenience to be integrated int…
Active Label Refinement for Robust Training of Imbalanced Medical Image Classification Tasks in the Presence of High Label Noise
Center for Imaging Science, Rochester Institute of Technology（罗切斯特理工学院成像科学中心）；University of Aberdeen（阿伯丁大学）；Biomedical Engineering, Rochester Institute of Technology（罗切斯特理工学院生物医学工程系）
University of Granada（格拉纳达大学）；University of Jaén（哈恩大学）
Multilabel classification is an emergent data mining task with a broad range of real world applications. Learning from imbalanced multilabel data is being deeply studied latterly, and several resampling methods have been proposed in the literature. The unequal label distribution in most multilabel datasets, with disparate imbalance levels, could be a handicap while learning new classifiers. In addition, this characteristic challenges many of the existent preprocessing algorithms. Furthermore, the concurrence between imbalanced labels can make harder the learning from certain labels. These are …
Pseudo-labels are confident predictions made on unlabeled target data by a classifier trained on labeled source data. They are widely used for adapting a model to unlabeled data, e.g., in a semi-supervised learning setting. Our key insight is that pseudo-labels are naturally imbalanced due to intrinsic data similarity, even when a model is trained on balanced source data and evaluated on balanced target data. If we address this previously unknown imbalanced classification problem arising from pseudo-labels instead of ground-truth training labels, we could remove model biases towards false majo…
Learning against label noise is a vital topic to guarantee a reliable performance for deep neural networks. Recent research usually refers to dynamic noise modeling with model output probabilities and loss values, and then separates clean and noisy samples. These methods have gained notable success. However, unlike cherry-picked data, existing approaches often cannot perform well when facing imbalanced datasets, a common scenario in the real world. We thoroughly investigate this phenomenon and point out two major issues that hinder the performance, i.e., \emph{inter-class loss distribution dis…
Extreme Multi-label Text Classification (XMC) involves learning a classifier that can assign an input with a subset of most relevant labels from millions of label choices. Recent approaches, such as XR-Transformer and LightXML, leverage a transformer instance to achieve state-of-the-art performance. However, in this process, these approaches need to make various trade-offs between performance and computational requirements. A major shortcoming, as compared to the Bi-LSTM based AttentionXML, is that they fail to keep separate feature representations for each resolution in a label tree. We thus …
(Partial) ranking loss is a commonly used evaluation measure for multi-label classification, which is usually optimized with convex surrogates for computational efficiency. Prior theoretical work on multi-label ranking mainly focuses on (Fisher) consistency analyses. However, there is a gap between existing theory and practice -- some pairwise losses can lead to promising performance but lack consistency, while some univariate losses are consistent but usually have no clear superiority in practice. In this paper, we attempt to fill this gap through a systematic study from two complementary per…
Zhejiang University（浙江大学）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；Chongqing University（重庆大学）；RIKEN（理化学研究所）
Partial-label learning (PLL) is a peculiar weakly-supervised learning task where the training samples are generally associated with a set of candidate labels instead of single ground truth. While a variety of label disambiguation methods have been proposed in this domain, they normally assume a class-balanced scenario that may not hold in many real-world applications. Empirically, we observe degenerated performance of the prior methods when facing the combinatorial challenge from the long-tailed distribution and partial-labeling. In this work, we first identify the major reasons that the prior…
Most studies on learning from noisy labels rely on unrealistic models of i.i.d. label noise, such as class-conditional transition matrices. More recent work on instance-dependent noise models are more realistic, but assume a single generative process for label noise across the entire dataset. We propose a more principled model of label noise that generalizes instance-dependent noise to multiple labelers, based on the observation that modern datasets are typically annotated using distributed crowdsourcing methods. Under our labeler-dependent model, label noise manifests itself under two modalit…
Yonsei University（延世大学）；NAVER AI Lab（NAVER AI实验室）；UNIST（蔚山科学技术院）
Every recent image-to-image translation model inherently requires either image-level (i.e. input-output pairs) or set-level (i.e. domain labels) supervision. However, even set-level supervision can be a severe bottleneck for data collection in practice. In this paper, we tackle image-to-image translation in a fully unsupervised setting, i.e., neither paired images nor domain labels. To this end, we propose a truly unsupervised image-to-image translation model (TUNIT) that simultaneously learns to separate image domains and translates input images into the estimated domains. Experimental result…
Horizon Robotics（地平线机器人）；University at Buffalo（布法罗大学）；Tsinghua University（清华大学）
Knowledge distillation is an effective approach to leverage a well-trained network or an ensemble of them, named as the teacher, to guide the training of a student network. The outputs from the teacher network are used as soft labels for supervising the training of a new network. Recent studies \citep{muller2019does,yuan2020revisiting} revealed an intriguing property of the soft labels that making labels soft serves as a good regularization to the student network. From the perspective of statistical learning, regularization aims to reduce the variance, however how bias and variance change is n…
Medical image classification is often challenging for two reasons: a lack of labelled examples due to expensive and time-consuming annotation protocols, and imbalanced class labels due to the relative scarcity of disease-positive individuals in the wider population. Semi-supervised learning (SSL) methods exist for dealing with a lack of labels, but they generally do not address the problem of class imbalance. In this study we propose Adaptive Blended Consistency Loss (ABCL), a drop-in replacement for consistency loss in perturbation-based SSL methods. ABCL counteracts data skew by adaptively m…
Simon Fraser University（西蒙弗雷泽大学）；Borealis AI（Borealis人工智能研究院）
Data imbalance, in which a plurality of the data samples come from a small proportion of labels, poses a challenge in training deep neural networks. Unlike classification, in regression the labels are continuous, potentially boundless, and form a natural ordering. These distinct features of regression call for new techniques that leverage the additional information encoded in label-space relationships. This paper presents the RankSim (ranking similarity) regularizer for deep imbalanced regression, which encodes an inductive bias that samples that are closer in label space should also be closer…
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；NLPR, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所模式识别国家重点实验室）
Partial-label learning (PLL) is an important branch of weakly supervised learning where the single ground truth resides in a set of candidate labels, while the research rarely considers the label imbalance. A recent study for imbalanced partial-Label learning proposed that the combinatorial challenge of partial-label learning and long-tail learning lies in matching between a decent marginal prior distribution with drawing the pseudo labels. However, we believe that even if the pseudo label matches the prior distribution, the tail classes will still be difficult to learn because the total weigh…
Network Embedding with Completely-imbalanced Labels
Department of Computer Science and Technology, University of Science and Technology Beijing（计算机科学与技术系，北京科技大学）；School of Software, Tsinghua University（软件学院，清华大学）；Department of Computer Science, University of Illinois at Chicago（计算机科学系，伊利诺伊大学香槟分校）
Inception Institute of Artificial Intelligence（初始人工智能研究院）；University of Macau（澳门大学）；Terminus Group（特斯联集团）
The pioneering method for unsupervised meta-learning, CACTUs, is a clustering-based approach with pseudo-labeling. This approach is model-agnostic and can be combined with supervised algorithms to learn from unlabeled data. However, it often suffers from label inconsistency or limited diversity, which leads to poor performance. In this work, we prove that the core reason for this is lack of a clustering-friendly property in the embedding space. We address this by minimizing the inter- to intra-class similarity ratio to provide clustering-friendly embedding features, and validate our approach t…
Predicting the subcellular localization of proteins is an important and challenging problem. Traditional experimental approaches are often expensive and time-consuming. Consequently, a growing number of research efforts employ a series of machine learning approaches to predict the subcellular location of proteins. There are two main challenges among the state-of-the-art prediction methods. First, most of the existing techniques are designed to deal with multi-class rather than multi-label classification, which ignores connections between multiple labels. In reality, multiple locations of parti…
Automatic analysis of the video is one of most complex problems in the fields of computer vision and machine learning. A significant part of this research deals with (human) activity recognition (HAR) since humans, and the activities that they perform, generate most of the video semantics. Video-based HAR has applications in various domains, but one of the most important and challenging is HAR in sports videos. Some of the major issues include high inter- and intra-class variations, large class imbalance, the presence of both group actions and single player actions, and recognizing simultaneou…
The capability of the traditional semi-supervised learning (SSL) methods is far from real-world application due to severely biased pseudo-labels caused by (1) class imbalance and (2) class distribution mismatch between labeled and unlabeled data. This paper addresses such a relatively under-explored problem. First, we propose a general pseudo-labeling framework that class-adaptively blends the semantic pseudo-label from a similarity-based classifier to the linear one from the linear classifier, after making the observation that both types of pseudo-labels have complementary properties in terms…
Neural Processing Research Center, Seoul National University（首尔大学神经处理研究中心）
Continual learning from a sequential stream of data is a crucial challenge for machine learning research. Most studies have been conducted on this topic under the single-label classification setting along with an assumption of balanced label distribution. This work expands this research horizon towards multi-label classification. In doing so, we identify unanticipated adversity innately existent in many multi-label datasets, the long-tailed distribution. We jointly address the two independently solved problems, Catastropic Forgetting and the long-tailed label distribution by first empirically …
Active learning typically focuses on training a model on few labeled examples alone, while unlabeled ones are only used for acquisition. In this work we depart from this setting by using both labeled and unlabeled data during model training across active learning cycles. We do so by using unsupervised feature learning at the beginning of the active learning pipeline and semi-supervised learning at every active learning cycle, on all available data. The former has not been investigated before in active learning, while the study of latter in the context of deep learning is scarce and recent find…
MIT Computer Science & Artificial Intelligence Laboratory（麻省理工学院计算机科学与人工智能实验室）；Department of Computer Science, Rutgers University（罗格斯大学计算机科学系）
Real-world data often exhibit imbalanced distributions, where certain target values have significantly fewer observations. Existing techniques for dealing with imbalanced data focus on targets with categorical indices, i.e., different classes. However, many tasks involve continuous targets, where hard boundaries between classes do not exist. We define Deep Imbalanced Regression (DIR) as learning from such imbalanced data with continuous targets, dealing with potential missing data for certain target values, and generalizing to the entire target range. Motivated by the intrinsic difference betw…
Transductive graph-based semi-supervised learning methods usually build an undirected graph utilizing both labeled and unlabeled samples as vertices. Those methods propagate label information of labeled samples to neighbors through their edges in order to get the predicted labels of unlabeled samples. Most popular semi-supervised learning approaches are sensitive to initial label distribution happened in imbalanced labeled datasets. The class boundary will be severely skewed by the majority classes in an imbalanced classification. In this paper, we proposed a simple and effective approach to a…
School of Information Science and Engineering（信息科学与工程学院）；Shandong University（山东大学）
Class imbalance, which is also called long-tailed distribution, is a common problem in classification tasks based on machine learning. If it happens, the minority data will be overwhelmed by the majority, which presents quite a challenge for data science. To address the class imbalance problem, researchers have proposed lots of methods: some people make the data set balanced (SMOTE), some others refine the loss function (Focal Loss), and even someone has noticed the value of labels influences class-imbalanced learning (Yang and Xu. Rethinking the value of labels for improving class-imbalanced …
We propose a highly data-efficient active learning framework for image classification. Our novel framework combines: (1) unsupervised representation learning of a Convolutional Neural Network and (2) the Gaussian Process (GP) method, in sequence to achieve highly data and label efficient classifications. Moreover, both elements are less sensitive to the prevalent and challenging class imbalance issue, thanks to the (1) feature learned without labels and (2) the Bayesian nature of GP. The GP-provided uncertainty estimates enable active learning by ranking samples based on the uncertainty and se…
Modern systems that rely on Machine Learning (ML) for predictive modelling, may suffer from the cold-start problem: supervised models work well but, initially, there are no labels, which are costly or slow to obtain. This problem is even worse in imbalanced data scenarios, where labels of the positive class take longer to accumulate. We propose an Active Learning (AL) system for datasets with orders of magnitude of class imbalance, in a cold start streaming scenario. We present a computationally efficient Outlier-based Discriminative AL approach (ODAL) and design a novel 3-stage sequence of AL…
University of California, Santa Barbara（加州大学圣巴巴拉分校）；University of California, Riverside（加州大学河滨分校）；University of British Columbia（不列颠哥伦比亚大学）
The goal in label-imbalanced and group-sensitive classification is to optimize relevant metrics such as balanced error and equal opportunity. Classical methods, such as weighted cross-entropy, fail when training deep nets to the terminal phase of training (TPT), that is training beyond zero training error. This observation has motivated recent flurry of activity in developing heuristic alternatives following the intuitive mechanism of promoting larger margin for minorities. In contrast to previous heuristics, we follow a principled analysis explaining how different loss adjustments affect marg…
Toyota Technological Institute at Chicago（芝加哥丰田技术研究院）；University of Chicago（芝加哥大学）
Deep Convolutional Neural Networks (DCNN) has shown excellent performance in a variety of machine learning tasks. This manuscript presents Deep Convolutional Neural Fields (DeepCNF), a combination of DCNN with Conditional Random Field (CRF), for sequence labeling with highly imbalanced label distribution. The widely-used training methods, such as maximum-likelihood and maximum labelwise accuracy, do not work well on highly imbalanced data. To handle this, we present a new training algorithm called maximum-AUC for DeepCNF. That is, we train DeepCNF by directly maximizing the empirical Area Unde…
Movie genre classification is an active research area in machine learning. However, due to the limited labels available, there can be large semantic variations between movies within a single genre definition. We expand these 'coarse' genre labels by identifying 'fine-grained' semantic information within the multi-modal content of movies. By leveraging pre-trained 'expert' networks, we learn the influence of different combinations of modes for multi-label genre classification. Using a contrastive loss, we continue to fine-tune this 'coarse' genre classification network to identify high-level in…
In document classification for, e.g., legal and biomedical text, we often deal with hundreds of classes, including very infrequent ones, as well as temporal concept drift caused by the influence of real world events, e.g., policy changes, conflicts, or pandemics. Class imbalance and drift can sometimes be mitigated by resampling the training data to simulate (or compensate for) a known target distribution, but what if the target distribution is determined by unknown future events? Instead of simply resampling uniformly to hedge our bets, we focus on the underlying optimization algorithms used …
Stanford University（斯坦福大学）；Harvard University（哈佛大学）；Toyota Research Institute（丰田研究所）
Real-world large-scale datasets are heteroskedastic and imbalanced -- labels have varying levels of uncertainty and label distributions are long-tailed. Heteroskedasticity and imbalance challenge deep learning algorithms due to the difficulty of distinguishing among mislabeled, ambiguous, and rare examples. Addressing heteroskedasticity and imbalance simultaneously is under-explored. We propose a data-dependent regularization technique for heteroskedastic datasets that regularizes different regions of the input space differently. Inspired by the theoretical derivation of the optimal regulariza…
