Adversarial training has been proven to be one of the most effective techniques to defend against adversarial examples. The majority of existing adversarial training methods assume that every class in the training data is equally distributed. However, in reality, some classes often have a large number of training data while others only have a very limited amount. Recent studies have shown that the performance of adversarial training will degrade drastically if the training data is imbalanced. In this paper, we propose a simple yet effective framework to enhance the robustness of DNN models under imbalanced scenarios. Our framework, Imb-Mix, first augments the training dataset by generating multiple adversarial examples for samples in the minority classes. This is done by first adding random noise to the original adversarial examples created by one specific adversarial attack method. It then constructs Mixup-mimic mixed examples upon the augmented dataset used by adversarial training. In addition, we theoretically prove the regularization effect of our Mixup-mimic mixed examples generation technique in Imb-Mix. Extensive experiments on various imbalanced datasets verify the effectiveness of the proposed framework.

Recent studies suggest that "memorization" is one necessary factor for overparameterized deep neural networks (DNNs) to achieve optimal performance. Specifically, the perfectly fitted DNNs can memorize the labels of many atypical samples, generalize their memorization to correctly classify test atypical samples and enjoy better test performance. While, DNNs which are optimized via adversarial training algorithms can also achieve perfect training performance by memorizing the labels of atypical samples, as well as the adversarially perturbed atypical samples. However, adversarially trained models always suffer from poor generalization, with both relatively low clean accuracy and robustness on the test set. In this work, we study the effect of memorization in adversarial trained DNNs and disclose two important findings: (a) Memorizing atypical samples is only effective to improve DNN's accuracy on clean atypical samples, but hardly improve their adversarial robustness and (b) Memorizing certain atypical samples will even hurt the DNN's performance on typical samples. Based on these two findings, we propose Benign Adversarial Training (BAT) which can facilitate adversarial training to avoid fitting "harmful" atypical samples and fit as more "benign" atypical samples as possible. In our experiments, we validate the effectiveness of BAT, and show that it can achieve better clean accuracy vs. robustness trade-off than baseline methods, in benchmark datasets for image classification.

A fundamental task for knowledge graphs (KGs) is knowledge graph completion (KGC). It aims to predict unseen edges by learning representations for all the entities and relations in a KG. A common concern when learning representations on traditional graphs is degree bias. It can affect graph algorithms by learning poor representations for lower-degree nodes, often leading to low performance on such nodes. However, there has been limited research on whether there exists degree bias for embedding-based KGC and how such bias affects the performance of KGC. In this paper, we validate the existence of degree bias in embedding-based KGC and identify the key factor to degree bias. We then introduce a novel data augmentation method, KG-Mixup, to generate synthetic triples to mitigate such bias. Extensive experiments have demonstrated that our method can improve various embedding-based KGC methods and outperform other methods tackling the bias problem on multiple benchmark datasets. 1

Adversarial training has been empirically proven to be one of the most effective and reliable defense methods against adversarial attacks. However, the majority of existing studies are focused on balanced datasets, where each class has a similar amount of training examples. Research on adversarial training with imbalanced training datasets is rather limited. As the initial effort to investigate this problem, we reveal the facts that adversarially trained models present two distinguished behaviors from naturally trained models in imbalanced datasets: (1) Compared to natural training, adversarially trained models can suffer much worse performance on under-represented classes, when the training dataset is extremely imbalanced. (2) Traditional reweighting strategies which assign large weights to underrepresented classes will drastically hurt the model’s performance on well-represented classes. In this paper, to further understand our observations, we theoretically show that the poor data separability is one key reason causing this strong tension between under-represented and well-represented classes. Motivated by this finding, we propose the Separable Reweighted Adversarial Training (SRAT) framework to facilitate adversarial training under imbalanced scenarios, by learning more separable features for different classes. Extensive experiments on various datasets verify the effectiveness of the proposed framework.

Although deep neural networks (DNNs) have been successfully deployed in various real-world application scenarios, recent studies demonstrated that DNNs are extremely vulnerable to adversarial attacks. By introducing visually imperceptible perturbations into benign inputs, the attacker can manipulate a DNN model into providing wrong predictions. For practitioners who are applying DNNs into real-world problems, understanding the characteristics of different kinds of attacks will not only help them improve the robustness of their models, but also can help them have deeper insights into the working mechanism of DNNs. In this tutorial, we provide a comprehensive overview of the recent advances of adversarial learning, including both attack methods and defense methods. Specifically, we first give a detailed introduction of various types of evasion attacks, followed by a series of representative defense methods against evasion attacks. We then discuss different poisoning attack methods, followed by several defense methods against poisoning attacks. In addition, besides introducing attack methods working in the digital setting, we also introduce attack methods designed for threatening physical world systems. Finally, we present DeepRobust, a PyTorch adversarial learning library which aims to build a comprehensive and easy-to-use platform to foster this research field. Via our tutorial, audience can grasp the main ideas of adversarial attacks and defenses and obtain a deep insight of the robustness of DNNs. The tutorial official website is available at https://sites.google.com/view/kdd22-tutorial-adv-learn/.

Crowdsourcing has proven to be a cost-effective way to meet the demands for labeled training data in supervised deep learning models. However, crowdsourced labels are often inconsistent and noisy due to cognitive and expertise differences among crowd workers. Existing approaches either infer latent true labels from noisy crowdsourced labels or learn a discriminative model directly from the crowdsourced labeled data, assuming the latent true label distribution is class-balanced. Unfortunately, in many real-world applications, the true label distribution typically is imbalanced across classes. Therefore, in this paper, we address the problem of learning from crowdsourced labeled data with an imbalanced true label distribution. We propose a new framework, named “Learning from Imbalanced Crowdsourced Labeled Data” (ICED), which simultaneously infers true labels from imbalanced crowdsourced labeled data and achieves high accuracy on downstream tasks such as classification. The ICED framework consists of two modules, i.e., a true label inference module and a synthetic data generation module, that augment each other iteratively. Extensive experiments conducted on both synthetic and real-world datasets demonstrate the effectiveness of the ICED framework. Our code is available at https://github.com/wentao-repo/ICED.

The vulnerability of deep neural network (DNN) models has been verified by the existence of adversarial examples. By exploiting slight changes to input examples, the generated adversarial examples can easily cause well trained DNN models make wrong predictions. Many defense methods have been proposed to improve the robustness of DNN models against adversarial examples. Among them, adversarial training has been empirically proven to be one of the most effective methods. Almost all existing studies about adversarial training are focused on balanced datasets, where each class has an equal amount of training examples. However, as datasets collected in real-world applications cannot guarantee all contained classes are uniformly distributed, it would be much challenging to obtain robust models in those real applications where the available training datasets are imbalanced. As the initial effort to study this problem, we first investigate the different behaviors between adversarially trained models and naturally trained models using imbalanced training datasets and then explore possible solutions to facilitate adversarial training under imbalanced settings.

Representation learning has been proven to play an important role in the unprecedented success of machine learning models in numerous tasks, such as machine translation, face recognition and recommendation. The majority of existing representation learning approaches often require a large number of consistent and noise-free labels. However, due to various reasons such as budget constraints and privacy concerns, labels are very limited in many real-world scenarios. Directly applying standard representation learning approaches on small labeled data sets will easily run into over-fitting problems and lead to sub-optimal solutions. Even worse, in some domains such as education, the limited labels are usually annotated by multiple workers with diverse expertise, which yields noises and inconsistency in such crowdsourcing settings. In this paper, we propose a novel framework which aims to learn effective representations from limited data with crowdsourced labels. Specifically, we design a grouping based deep neural network to learn embeddings from a limited number of training samples and present a Bayesian confidence estimator to capture the inconsistency among crowdsourced labels. Furthermore, to expedite the training process, we develop a hard example selection procedure to adaptively pick up training examples that are misclassified by the model. Extensive experiments conducted on three real-world data sets demonstrate the superiority of our framework on learning representations from limited data with crowdsourced labels, comparing with various state-of-the-art baselines. In addition, we provide a comprehensive analysis on each of the main components of our proposed framework and also introduce the promising results it achieved in our real production to fully understand the proposed framework. To encourage reproducible results, we make our code available online athttps://github.com/tal-ai/RECLE.

Deep neural networks (DNNs) have achieved unprecedented accomplishments in various machine learning tasks. However, recent studies demonstrate that DNNs are extremely vulnerable to adversarial examples. They are manually synthesized input samples which look benign but can severely fool the prediction of DNN models. For machine learning practitioners who are applying DNNs, understanding the behavior of adversarial examples will not only help them improve the safety of their models, but also can help them have deeper insights into the working mechanism of the DNNs. In this tutorial, we provide a comprehensive overview on the recent advances of adversarial examples and their countermeasures, from both practical and theoretical perspectives. From the practical aspect, we give a detailed introduction of the popular algorithms to generate adversarial examples under different adversary's goals. We also discuss how the defending strategies are developed to resist these attacks, and how new attacks come out to break these defenses. From the theoretical aspect, we discuss a series of intrinsic behaviors of robust DNNs which are different from traditional DNNs, especially about their optimization and generalization properties. Finally, we introduce DeepRobust, a Pytorch adversarial learning library which aims to build a comprehensive and easy-to-use platform to foster this research field. Via our tutorial, the audience can grip the main ideas of adversarial attacks and defenses and gain a deep insight of DNN's robustness. The tutorial official website is at https://sites.google.com/view/kdd21-tutorial-adv-robust.

Positive and unlabeled (PU) learning aims to obtain a well-performed classifier via an incomplete binary training set, in which only a part of labels of one category is known while the rest are unknown. However, in many real-world applications such as image recognition, the collected data samples often involve more than two categories. Moreover, only a small portion of the collected samples might have associated labels due to some practical reasons, and these labeled samples cannot always cover all the categories. We refer to this type of data as incomplete labeled data. In this paper, we first formally define the incomplete labeled data learning problem and then aim to tackle it via adversarial data generation. Specifically, we propose a novel generative framework LILA, which can produce synthetic labeled samples for both partially labeled categories and unlabeled categories. To enforce that the generated samples for unlabeled categories can associate with correct labels, we integrate two active learning processes into the LILA framework for selecting unlabeled samples in the collected sample set to query their labels effectively. After LILA has been well trained, a classifier can be trained on the balanced augmented data set consisting of both generated and original labeled samples. Extensive experiments on real image data demonstrate the effectiveness of our proposed framework. We release the implementation of the proposed framework via https://github.com/wentao-repo/LILA.

In many real-world classification applications such as fake news detection, the training data can be extremely imbalanced, which brings challenges to existing classifiers as the majority classes dominate the loss functions of classifiers. Oversampling techniques such as SMOTE are effective approaches to tackle the class imbalance problem by producing more synthetic minority samples. Despite their success, the majority of existing oversampling methods only consider local data distributions when generating minority samples, which can result in noisy minority samples that do not fit global data distributions or interleave with majority classes. Hence, in this paper, we study the class imbalance problem by simultaneously exploring local and global data information since: (i) the local data distribution could give detailed information for generating minority samples; and (ii) the global data distribution could provide guidance to avoid generating outliers or samples that interleave with majority classes. Specifically, we propose a novel framework GL-GAN, which leverages the SMOTE method to explore local distribution in a learned latent space and employs GAN to capture the global information, so that synthetic minority samples can be generated under even extremely imbalanced scenarios. Experimental results on diverse real data sets demonstrate the effectiveness of our GL-GAN framework in producing realistic and discriminative minority samples for improving the classification performance of various classifiers on imbalanced training data. Our code is available at https://github.com/wentao-repo/GL-GAN.

Many systems, such as distributed operating systems, complex networks, and high throughput web-based applications, are continuously generating large volume of event logs. These logs contain useful information to help system administrators to understand the system running status and to pinpoint the system failures. Generally, due to the scale and complexity of modern systems, the generated logs are beyond the analytic power of human beings. Therefore, it is imperative to develop a comprehensive log analysis system to support effective system management. Although a number of log mining techniques have been proposed to address specific log analysis use cases, few research and industrial efforts have been paid on providing integrated systems with an end-to-end solution to facilitate the log analysis routines.

Large-scale time series data are prevalent across diverse application domains including system management, biomedical informatics, social networks, finance, etc. Temporal dependency discovery performs an essential part to identify the hidden interactions among the observed time series and helps to gain more insight into the behavior of the applications. However, the time-varying sparsity of the interactions among time series often poses a big challenge to temporal dependency discovery in practice. This paper formulates the temporal dependency problem with a novel Bayesian model allowing for both the sparsity and evolution of the hidden interactions among the observed time series. Taking advantage of the Bayesian modeling, an online inference method is proposed for time-varying temporal dependency discovery. Extensive empirical studies on both the synthetic and real application time series data are conducted to demonstrate the effectiveness and the efficiency of the proposed method.

In disaster management, people are interested in the development and the evolution of the disasters. If they intend to track the information of the disaster, they will be overwhelmed by the large number of disaster-related documents, microblogs, and news, etc. To support disaster management and minimize the loss during the disaster, it is necessary to efficiently and effectively collect, deliver, summarize, and analyze the disaster information, letting people in affected area quickly gain an overview of the disaster situation and improve their situational awareness.