In the presence of noisy or incorrect labels, neural networks have the undesirable tendency to memorize information about the noise. Standard regularization techniques such as dropout, weight decay or data augmentation sometimes help, but do not prevent this behavior. If one considers neural network weights as random variables that depend on the data and stochasticity of training, the amount of memorized information can be quantified with the Shannon mutual information between weights and the vector of all training labels given inputs, $I(w ; \mathbf{y} \mid \mathbf{x})$. We show that for any training algorithm, low values of this term correspond to reduction in memorization of label-noise and better generalization bounds. To obtain these low values, we propose training algorithms that employ an auxiliary network that predicts gradients in the final layers of a classifier without accessing labels. We illustrate the effectiveness of our approach on versions of MNIST, CIFAR-10, and CIFAR-100 corrupted with various noise models, and on a large-scale dataset Clothing1M that has noisy labels.
Saab AB（萨博集团）；Chalmers University of Technology（查尔姆斯理工大学）
Following the success of supervised learning, semi-supervised learning (SSL) is now becoming increasingly popular. SSL is a family of methods, which in addition to a labeled training set, also use a sizable collection of unlabeled data for fitting a model. Most of the recent successful SSL methods are based on pseudo-labeling approaches: letting confident model predictions act as training labels. While these methods have shown impressive results on many benchmark datasets, a drawback of this approach is that not all unlabeled data are used during training. We propose a new SSL algorithm, Doubl…
Sequence labelling is the task of assigning categorical labels to a data sequence. In Natural Language Processing, sequence labelling can be applied to various fundamental problems, such as Part of Speech (POS) tagging, Named Entity Recognition (NER), and Chunking. In this study, we propose a method to add various linguistic features to the neural sequence framework to improve sequence labelling. Besides word level knowledge, sense embeddings are added to provide semantic information. Additionally, selective readings of character embeddings are added to capture contextual as well as morphologi…
Deep learning has become the method of choice in many application domains of machine learning in recent years, especially for multi-class classification tasks. The most common loss function used in this context is the cross-entropy loss, which reduces to the log loss in the typical case when there is a single correct response label. While this loss is insensitive to the identity of the assigned class in the case of misclassification, in practice it is often the case that some errors may be more detrimental than others. Here we present the bilinear-loss (and related log-bilinear-loss) which dif…
Improving the Convergence Rate of Ray Search Optimization for Query-Efficient Hard-Label Attacks
Institute of Cyberspace Security, Zhejiang University of Technology（浙江工业大学网络空间安全研究院）；JQ Investments（JQ投资）；Binjiang Institute of Artificial Intelligence, ZJUT（浙江工业大学滨江人工智能研究院）
Label ranking is a prediction task which deals with learning a mapping between an instance and a ranking (i.e., order) of labels from a finite set, representing their relevance to the instance. Boosting is a well-known and reliable ensemble technique that was shown to often outperform other learning algorithms. While boosting algorithms were developed for a multitude of machine learning tasks, label ranking tasks were overlooked. In this paper, we propose a boosting algorithm which was specifically designed for label ranking tasks. Extensive evaluation of the proposed algorithm on 24 semi-synt…
In recent years, multi-label classification problem has become a controversial issue. In this kind of classification, each sample is associated with a set of class labels. Ensemble approaches are supervised learning algorithms in which an operator takes a number of learning algorithms, namely base-level algorithms and combines their outcomes to make an estimation. The simplest form of ensemble learning is to train the base-level algorithms on random subsets of data and then let them vote for the most popular classifications or average the predictions of the base-level algorithms. In this study…
Technical University of Munich（慕尼黑工业大学）；Siemens AG（西门子股份公司）
Diagnosing diseases such as leukemia or anemia requires reliable counts of blood cells. Hematologists usually label and count microscopy images of blood cells manually. In many cases, however, cells in different maturity states are difficult to distinguish, and in combination with image noise and subjectivity, humans are prone to make labeling mistakes. This results in labels that are often not reproducible, which can directly affect the diagnoses. We introduce TIMELY, a probabilistic model that combines pseudotime inference methods with inhomogeneous hidden Markov trees, which addresses this …
ING Wholesale Banking Advanced Analytics（ING批发银行高级分析部）；University of Amsterdam（阿姆斯特丹大学）；Feebris（Feebris公司）
The availability of labelled data is one of the main limitations in machine learning. We can alleviate this using weak supervision: a framework that uses expert-defined rules $\boldsymbolλ$ to estimate probabilistic labels $p(y|\boldsymbolλ)$ for the entire data set. These rules, however, are dependent on what experts know about the problem, and hence may be inaccurate or may fail to capture important parts of the problem-space. To mitigate this, we propose Active WeaSuL: an approach that incorporates active learning into weak supervision. In Active WeaSuL, experts do not only define rules, bu…
University of Cambridge（剑桥大学）；Université Bordeaux（波尔多大学）；ByteDance（字节跳动）；Taibah University（塔伊巴大学）；National University of Singapore（新加坡国立大学）；Yale-NUS College（耶鲁-新加坡国立大学学院）
Semi-supervised classification is a great focus of interest, as in real-world scenarios obtaining labels is expensive, time-consuming and might require expert knowledge. This has motivated the fast development of semi-supervised techniques, whose performance is on a par with or better than supervised approaches. A current major challenge for semi-supervised techniques is how to better handle the network calibration and confirmation bias problems for improving performance. In this work, we argue that energy models are an effective alternative to such problems. With this motivation in mind, we p…
Improving the generalization of deep networks is an important open challenge, particularly in domains without plentiful data. The mixup algorithm improves generalization by linearly interpolating a pair of examples and their corresponding labels. These interpolated examples augment the original training set. Mixup has shown promising results in various classification tasks, but systematic analysis of mixup in regression remains underexplored. Using mixup directly on regression labels can result in arbitrarily incorrect labels. In this paper, we propose a simple yet powerful algorithm, C-Mixup,…
Fine-grained annotations---e.g. dense image labels, image segmentation and text tagging---are useful in many ML applications but they are labor-intensive to generate. Moreover there are often systematic, structured errors in these fine-grained annotations. For example, a car might be entirely unannotated in the image, or the boundary between a car and street might only be coarsely annotated. Standard ML training on data with such structured errors produces models with biases and poor performance. In this work, we propose a novel framework of Error-Correcting Networks (ECN) to address the chall…
Massachusetts Institute of Technology（麻省理工学院）；EECS（电气工程与计算机科学系（麻省理工学院））
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 demonstra…
The University of Auckland（奥克兰大学）；The University of Waikato（怀卡托大学）
Multi-label learning predicts a subset of labels from a given label set for an unseen instance while considering label correlations. A known challenge with multi-label classification is the long-tailed distribution of labels. Many studies focus on improving the overall predictions of the model and thus do not prioritise tail-end labels. Improving the tail-end label predictions in multi-label classifications of medical text enables the potential to understand patients better and improve care. The knowledge gained by one or more infrequent labels can impact the cause of medical decisions and tre…
Mislabeled samples are ubiquitous in real-world datasets as rule-based or expert labeling is usually based on incorrect assumptions or subject to biased opinions. Neural networks can "memorize" these mislabeled samples and, as a result, exhibit poor generalization. This poses a critical issue in fault detection applications, where not only the training but also the validation datasets are prone to contain mislabeled samples. In this work, we propose a novel two-step framework for robust training with label noise. In the first step, we identify outliers (including the mislabeled samples) based …
Carnegie Mellon University（卡内基梅隆大学）；University of Tokyo（东京大学）
It has been hypothesized that label smoothing can reduce overfitting and improve generalization, and current empirical evidence seems to corroborate these effects. However, there is a lack of mathematical understanding of when and why such empirical improvements occur. In this paper, as a step towards understanding why label smoothing is effective, we propose a theoretical framework to show how label smoothing provides in controlling the generalization loss. In particular, we show that this benefit can be precisely formulated and identified in the label noise setting, where the training is par…
Modern neural network architectures have shown remarkable success in several large-scale classification and prediction tasks. Part of the success of these architectures is their flexibility to transform the data from the raw input representations (e.g. pixels for vision tasks, or text for natural language processing tasks) to one-hot output encoding. While much of the work has focused on studying how the input gets transformed to the one-hot encoding, very little work has examined the effectiveness of these one-hot labels. In this work, we demonstrate that more sophisticated label representati…
Recent work has uncovered the interesting (and somewhat surprising) finding that training models to be invariant to adversarial perturbations requires substantially larger datasets than those required for standard classification. This result is a key hurdle in the deployment of robust machine learning models in many real world applications where labeled data is expensive. Our main insight is that unlabeled data can be a competitive alternative to labeled data for training adversarially robust models. Theoretically, we show that in a simple statistical setting, the sample complexity for learnin…
There is growing evidence that converting targets to soft targets in supervised learning can provide considerable gains in performance. Much of this work has considered classification, converting hard zero-one values to soft labels---such as by adding label noise, incorporating label ambiguity or using distillation. In parallel, there is some evidence from a regression setting in reinforcement learning that learning distributions can improve performance. In this work, we investigate the reasons for this improvement, in a regression setting. We introduce a novel distributional regression loss, …
PRECISE Center（PRECISE中心）；University of Pennsylvania（宾夕法尼亚大学）
Providing reliable model uncertainty estimates is imperative to enabling robust decision making by autonomous agents and humans alike. While recently there have been significant advances in confidence calibration for trained models, examples with poor calibration persist in most calibrated models. Consequently, multiple techniques have been proposed that leverage label-invariant transformations of the input (i.e., an input manifold) to improve worst-case confidence calibration. However, manifold-based confidence calibration techniques generally do not scale and/or require expensive retraining …
While improving prediction accuracy has been the focus of machine learning in recent years, this alone does not suffice for reliable decision-making. Deploying learning systems in consequential settings also requires calibrating and communicating the uncertainty of predictions. To convey instance-wise uncertainty for prediction tasks, we show how to generate set-valued predictions from a black-box predictor that control the expected loss on future test points at a user-specified level. Our approach provides explicit finite-sample guarantees for any dataset by using a holdout set to calibrate t…
Unsupervised domain adaptation (UDA) transfers knowledge from a label-rich source domain to a different but related fully-unlabeled target domain. To address the problem of domain shift, more and more UDA methods adopt pseudo labels of the target samples to improve the generalization ability on the target domain. However, inaccurate pseudo labels of the target samples may yield suboptimal performance with error accumulation during the optimization process. Moreover, once the pseudo labels are generated, how to remedy the generated pseudo labels is far from explored. In this paper, we propose a…
A wide breadth of research has devised data augmentation approaches that can improve both accuracy and generalization performance for neural networks. However, augmented data can end up being far from the clean training data and what is the appropriate label is less clear. Despite this, most existing work simply uses one-hot labels for augmented data. In this paper, we show re-using one-hot labels for highly distorted data might run the risk of adding noise and degrading accuracy and calibration. To mitigate this, we propose a generic method AutoLabel to automatically learn the confidence in t…
In the recent trend of semi-supervised speech recognition, both self-supervised representation learning and pseudo-labeling have shown promising results. In this paper, we propose a novel approach to combine their ideas for end-to-end speech recognition model. Without any extra loss function, we utilize the Gradient Mask to optimize the model when training on pseudo-label. This method forces the speech recognition model to predict from the masked input to learn strong acoustic representation and make training robust to label noise. In our semi-supervised experiments, the method can improve the…
Labeling large image datasets with attributes such as facial age or object type is tedious and sometimes infeasible. Supervised machine learning methods provide a highly accurate solution, but require manual labels which are often unavailable. Zero-shot models (e.g., CLIP) do not require manual labels but are not as accurate as supervised ones, particularly when the attribute is numeric. We propose a new approach, CLIPPR (CLIP with Priors), which adapts zero-shot models for regression and classification on unlabelled datasets. Our method does not use any annotated images. Instead, we assume a …
LaTTiCe (UMR 8094)（LaTTiCe实验室（UMR 8094））；CNRS（法国国家科学研究中心）；ENS Paris（巴黎高等师范学院）；Université Sorbonne Nouvelle - Paris 3（索邦新巴黎第三大学）；PSL Research University（PSL研究大学）；USPC (Université Sorbonne Paris Cité)（索邦巴黎西岱大学）
In this paper we study different types of Recurrent Neural Networks (RNN) for sequence labeling tasks. We propose two new variants of RNNs integrating improvements for sequence labeling, and we compare them to the more traditional Elman and Jordan RNNs. We compare all models, either traditional or new, on four distinct tasks of sequence labeling: two on Spoken Language Understanding (ATIS and MEDIA); and two of POS tagging for the French Treebank (FTB) and the Penn Treebank (PTB) corpora. The results show that our new variants of RNNs are always more effective than the others.
Corporate Research, Robert Bosch GmbH（罗伯特·博世公司企业研究部）；Institute of Measurement, Control and Microtechnology, Ulm University（乌尔姆大学测量、控制与微技术研究所）
Reliable uncertainty estimation is crucial for robust object detection in autonomous driving. However, previous works on probabilistic object detection either learn predictive probability for bounding box regression in an un-supervised manner, or use simple heuristics to do uncertainty regularization. This leads to unstable training or suboptimal detection performance. In this work, we leverage our previously proposed method for estimating uncertainty inherent in ground truth bounding box parameters (which we call label uncertainty) to improve the detection accuracy of a probabilistic LiDAR-ba…
Improving Multi-Label Contrastive Learning by Leveraging Label Distribution
College of Computer Science and Software Engineering, Hohai University（河海大学计算机与软件学院）；State Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）
Cornell University（康奈尔大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
Our goal is procedural text comprehension, namely tracking how the properties of entities (e.g., their location) change with time given a procedural text (e.g., a paragraph about photosynthesis, a recipe). This task is challenging as the world is changing throughout the text, and despite recent advances, current systems still struggle with this task. Our approach is to leverage the fact that, for many procedural texts, multiple independent descriptions are readily available, and that predictions from them should be consistent (label consistency). We present a new learning framework that levera…
Improving Graph Neural Networks on Multi-node Tasks with the Labeling Trick
Institute for Artificial Intelligence Peking University（北京大学人工智能研究院）；School of Electrical and Computer Engineering Georgia Institute of Technology（佐治亚理工学院电气与计算机工程学院）
ABBYY（ABBYY公司）；Moscow Institute of Physics and Technology（莫斯科物理技术学院）
In this paper, we explore the ways to improve POS-tagging using various types of auxiliary losses and different word representations. As a baseline, we utilized a BiLSTM tagger, which is able to achieve state-of-the-art results on the sequence labelling tasks. We developed a new method for character-level word representation using feedforward neural network. Such representation gave us better results in terms of speed and performance of the model. We also applied a novel technique of pretraining such word representations with existing word vectors. Finally, we designed a new variant of auxilia…
Aristotle University of Thessaloniki（塞萨洛尼基亚里士多德大学）
Distantly-supervised relation extraction (RE) is an effective method to scale RE to large corpora but suffers from noisy labels. Existing approaches try to alleviate noise through multi-instance learning and by providing additional information, but manage to recognize mainly the top frequent relations, neglecting those in the long-tail. We propose REDSandT (Relation Extraction with Distant Supervision and Transformers), a novel distantly-supervised transformer-based RE method, that manages to capture a wider set of relations through highly informative instance and label embeddings for RE, by e…
Classes are not Clusters: Improving Label-based Evaluation of Dimensionality Reduction
Seoul National University（首尔国立大学）；University of California, Davis（加州大学戴维斯分校）；Qatar Computing Research Institute, Hamad Bin Khalifa University（哈马德·本·哈利法大学卡塔尔计算研究所）
The Chinese University of Hong Kong（香港中文大学）；Tsinghua University（清华大学）；Zhejiang Lab（之江实验室）；Tencent（腾讯）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）
Attaining the equilibrium state of a catalyst-adsorbate system is key to fundamentally assessing its effective properties, such as adsorption energy. Machine learning methods with finer supervision strategies have been applied to boost and guide the relaxation process of an atomic system and better predict its properties at the equilibrium state. In this paper, we present a novel graph neural network (GNN) supervision and prediction strategy DR-Label. The method enhances the supervision signal, reduces the multiplicity of solutions in edge representation, and encourages the model to provide no…
Deargen Inc.（Deargen公司）；Deargen USA Inc.（Deargen美国公司）
The standard empirical risk minimization (ERM) can underperform on certain minority groups (i.e., waterbirds in lands or landbirds in water) due to the spurious correlation between the input and its label. Several studies have improved the worst-group accuracy by focusing on the high-loss samples. The hypothesis behind this is that such high-loss samples are \textit{spurious-cue-free} (SCF) samples. However, these approaches can be problematic since the high-loss samples may also be samples with noisy labels in the real-world scenarios. To resolve this issue, we utilize the predictive uncertai…
Bosch Center for Artificial Intelligence（博世人工智能中心）；University of Stuttgart（斯图加特大学）
Object type classification for automotive radar has greatly improved with recent deep learning (DL) solutions, however these developments have mostly focused on the classification accuracy. Before employing DL solutions in safety-critical applications, such as automated driving, an indispensable prerequisite is the accurate quantification of the classifiers' reliability. Unfortunately, DL classifiers are characterized as black-box systems which output severely over-confident predictions, leading downstream decision-making systems to false conclusions with possibly catastrophic consequences. We…
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…
Interdisciplinary Program in Artificial Intelligence, Seoul National University（人工智能跨学科项目，首尔国立大学）；Department of Computer Science and Engineering, Seoul National University（计算机科学与工程系，首尔国立大学）；Interdisciplinary Program in Bioinformatics, Seoul National University（生物信息学跨学科项目，首尔国立大学）；AIGENDRUG Co., Ltd., Seoul（AIGENDRUG公司，首尔）；Department of Artificial Intelligence, Inha University（人工智能系，inha大学）
