Adversarial Active Learning Research Articles

Active Machine Learning for Pre-procedural Prediction of Time-Varying Boundary Condition After Fontan Procedure Using Generative Adversarial Networks.

The Fontan procedure is the definitive palliation for pediatric patients born with single ventricles. Surgical planning for the Fontan procedure has emerged as a promising vehicle toward optimizing outcomes, where pre-operative measurements are used prospectively as post-operative boundary conditions for simulation. Nevertheless, actual post-operative measurements can be very different from pre-operative states, which raises questions for the accuracy of surgical planning. The goal of this study is to apply machine leaning techniques to describing pre-operative and post-operative vena caval flow conditions in Fontan patients in order to develop predictions of post-operative boundary conditions to be used in surgical planning. Based on a virtual cohort synthesized by lumped-parameter models, we proposed a novel diversity-aware generative adversarial active learning framework to successfully train predictive deep neural networks on very limited amount of cases that are generally faced by cardiovascular studies. Results of 14 groups of experiments uniquely combining different data query strategies, metrics, and data augmentation options with generative adversarial networks demonstrated that the highest overall prediction accuracy and coefficient of determination were exhibited by the proposed method. This framework serves as a first step toward deep learning for cardiovascular flow prediction/regression with reduced labeling requirements and augmented learning space.

Imbalanced COVID-19 vaccine sentiment classification with synthetic resampling coupled deep adversarial active learning

Imbalanced COVID-19 vaccine sentiment classification with synthetic resampling coupled deep adversarial active learning

Model-data-driven adversarial active learning for brain tumor segmentation

Active learning (AL) attempts to select informative samples in a dataset to minimize the number of required labels while maximizing the performance of the model. Current AL in segmentation tasks is limited to the expansion of popular classification-based methods including entropy, MC-dropout, etc. Meanwhile, most applications in the medical field are simply migrations that fail to consider the nature of medical images, such as high class imbalance, high domain difference, and data scarcity. In this study, we address these challenges and propose a novel AL framework for medical image segmentation task. Our approach introduces a pseudo-label-based filter addressing excessive blank patches in medical abnormalities segmentation tasks, e.g., lesions, and tumors, used before the AL selection. This filter helps reduce resource usage and allows the model to focus on selecting more informative samples. For the sample selection, we propose a novel query strategy that combines both model impact and data stability by employing adversarial attack. Furthermore, we harness the adversarial samples generated during the query process to enhance the robustness of the model. The experimental results verify our framework’s effectiveness over various state-of-the-art methods. Our proposed method only needs less than 14% annotated patches in 3D brain MRI multiple sclerosis (MS) segmentation tasks and 20% for Low-Grade Glioma (LGG) tumor segmentation to achieve competitive results with full supervision. These promising outcomes not only improve performance but alleviate the time burden associated with expert annotation, thereby facilitating further advancements in the field of medical image segmentation. Our code is available at https://github.com/HelenMa9998/adversarial_active_learning.

M-VAAL: Multimodal Variational Adversarial Active Learning for Downstream Medical Image Analysis Tasks.

Acquiring properly annotated data is expensive in the medical field as it requires experts, time-consuming protocols, and rigorous validation. Active learning attempts to minimize the need for large annotated samples by actively sampling the most informative examples for annotation. These examples contribute significantly to improving the performance of supervised machine learning models, and thus, active learning can play an essential role in selecting the most appropriate information in deep learning-based diagnosis, clinical assessments, and treatment planning. Although some existing works have proposed methods for sampling the best examples for annotation in medical image analysis, they are not task-agnostic and do not use multimodal auxiliary information in the sampler, which has the potential to increase robustness. Therefore, in this work, we propose a Multimodal Variational Adversarial Active Learning (M-VAAL) method that uses auxiliary information from additional modalities to enhance the active sampling. We applied our method to two datasets: i) brain tumor segmentation and multi-label classification using the BraTS2018 dataset, and ii) chest X-ray image classification using the COVID-QU-Ex dataset. Our results show a promising direction toward data-efficient learning under limited annotations.

Latent-Enhanced Variational Adversarial Active Learning Assisted Soft Sensor

As the acquisition of variables that measure quality is typically challenging, labeled samples for building a model for soft sensors are often inadequate. Additionally, owing to the installation of redundant sensors, high-dimensional process data with strong correlations are acquired. Therefore, in this study, a sample selection strategy for active learning, referred to as latent-enhanced variational adversarial active learning (LVAAL), is developed to enhance quality prediction performance with limited labeled data. The LVAAL method uses a minimax game to explore the latent representation of the original data. Specifically, a latent-enhanced variational autoencoder is used to deceive the adversarial network into predicting all samples, both labeled and unlabeled, as labeled. However, the adversarial network attempts to indicate the difference between latent representations. Subsequently, Gaussian process regression is adopted as a base model for LVAAL. With the proposed LVAAL selection strategy, informative unlabeled samples are incrementally selected, thereby enhancing the prediction performance. The application results for a numerical case and an industrial example demonstrate the advantages of LVAAL compared with existing active learning strategies.

A generative adversarial active learning method for mechanical layout generation

A generative adversarial active learning method for mechanical layout generation

Independency‐enhancing adversarial active learning

AbstractThe core idea of active learning is to obtain higher model performance with less annotation cost. This paper proposes an independency‐enhancing adversarial active learning method. Independency‐enhancing adversarial active learning is different from the previous methods and pays more attention to sample independence. Specifically, it is believed that the informativeness of a group of samples is related to sample independence rather than the simple sum of the informativeness of each sample in the group. Therefore, an independent sample selection module based on hierarchical clustering is designed to ensure sample independence. An adversarial approach is used to learn the feature representation of a sample and use the predicted loss value to label the state of the sample. Finally, samples are selected according to the uncertainty of the samples, the diversity of the samples and the independence of the samples. The experimental results on four datasets (CIFAR‐100, Caltech‐101, Cityscapes and BDD100K) demonstrate the effectiveness and superiority of independency‐enhancing adversarial active learning.

Efficient labeling of retinal fundus photographs using deep active learning.

To compare the performance of four deep active learning (DAL) approaches to optimize label efficiency for training diabetic retinopathy (DR) classification deep learning models. 88,702 color retinal fundus photographs from 44,351 patients with DR grades from the publicly available EyePACS dataset were used. Four DAL approaches [entropy sampling (ES), Bayesian active learning by disagreement (BALD), core set, and adversarial active learning (ADV)] were compared to conventional naive random sampling. Models were compared at various dataset sizes using Cohen's kappa (CK) and area under the receiver operating characteristic curve on an internal test set of 10,000 images. An independent test set of 3662 fundus photographs was used to assess generalizability. On the internal test set, 3 out of 4 DAL methods resulted in statistically significant performance improvements ( ) compared to random sampling for multiclass classification, with the largest observed differences in CK ranging from 0.051 for BALD to 0.053 for ES. Improvements in multiclass classification generalized to the independent test set, with the largest differences in CK ranging from 0.126 to 0.135. However, no statistically significant improvements were seen for binary classification. Similar performance was seen across DAL methods, except ADV, which performed similarly to random sampling. Uncertainty-based and feature descriptor-based deep active learning methods outperformed random sampling on both the internal and independent test sets at multiclass classification. However, binary classification performance remained similar across random sampling and active learning methods.

Deep entity matching with adversarial active learning

Deep entity matching with adversarial active learning

Automating Rapid Network Anomaly Detection With In-Band Network Telemetry

Network anomaly detection plays a significant role in Operation Administration and Maintenance (OAM). In this letter, we propose INT-detector, an automated and rapid network anomaly detection system, by combining In-band Network Telemetry (INT) and Deep Learning (DL). First, we build an INTbased telemetry prototype, enabling fine-grained monitoring by acquiring hop-by-hop device states. Then, we leverage Generative Adversarial Active Learning (GAAL) to detect anomalies without overreliance on the human intervention. Besides, we perform data preprocessing with low-pass filtering to eliminate transient traffic jitters for detecting more persistent anomalies. INT-detector is accurate and achieves 0.979 AUC on the collected INT dataset.

MTAAL: Multi-Task Adversarial Active Learning for Medical Named Entity Recognition and Normalization

Automated medical named entity recognition and normalization are fundamental for constructing knowledge graphs and building QA systems. When it comes to medical text, the annotation demands a foundation of expertise and professionalism. Existing methods utilize active learning to reduce costs in corpus annotation, as well as the multi-task learning strategy to model the correlations between different tasks. However, existing models do not take task-specific features for different tasks and diversity of query samples into account. To address these limitations, this paper proposes a multi-task adversarial active learning model for medical named entity recognition and normalization. In our model, the adversarial learning keeps the effectiveness of multi-task learning module and active learning module. The task discriminator eliminates the influence of irregular task-specific features. And the diversity discriminator exploits the heterogeneity between samples to meet the diversity constraint. The empirical results on two medical benchmarks demonstrate the effectiveness of our model against the existing methods.

Dual generative adversarial active learning

The purpose of active learning is to significantly reduce the cost of annotation while ensuring the good performance of the model. In this paper, we propose a novel active learning method based on the combination of pool and synthesis named dual generative adversarial active learning (DGAAL), which includes the functions of image generation and representation learning. This method includes two groups of generative adversarial network composed of a generator and two discriminators. One group is used for representation learning, and then this paper performs sampling based on the predicted value of the discriminator. The other group is used for image generation. The purpose is to generate samples which are similar to those obtained from sampling, so that samples with rich information can be fully utilized. In the sampling process, the two groups of network cooperate with each other to enable the generated samples to participate in sampling process, and to enable the discriminator for sampling to co-evolve. Thus, in the later stage of sampling, the problem of insufficient information for selecting samples based on the pool method is alleviated. In this paper, DGAAL is evaluated extensively on three data sets, and the results show that DGAAL not only has certain advantages over the existing methods in terms of model performance but can also further reduces the annotation cost.

Redundancy Removal Adversarial Active Learning Based on Norm Online Uncertainty Indicator.

Active learning aims to select the most valuable unlabelled samples for annotation. In this paper, we propose a redundancy removal adversarial active learning (RRAAL) method based on norm online uncertainty indicator, which selects samples based on their distribution, uncertainty, and redundancy. RRAAL includes a representation generator, state discriminator, and redundancy removal module (RRM). The purpose of the representation generator is to learn the feature representation of a sample, and the state discriminator predicts the state of the feature vector after concatenation. We added a sample discriminator to the representation generator to improve the representation learning ability of the generator and designed a norm online uncertainty indicator (Norm-OUI) to provide a more accurate uncertainty score for the state discriminator. In addition, we designed an RRM based on a greedy algorithm to reduce the number of redundant samples in the labelled pool. The experimental results on four datasets show that the state discriminator, Norm-OUI, and RRM can improve the performance of RRAAL, and RRAAL outperforms the previous state-of-the-art active learning methods.

Hyperspectral Image Classification with Feature-Oriented Adversarial Active Learning

Deep learning classifiers exhibit remarkable performance for hyperspectral image classification given sufficient labeled samples but show deficiency in the situation of learning with limited labeled samples. Active learning endows deep learning classifiers with the ability to alleviate this deficiency. However, existing active deep learning methods tend to underestimate the feature variability of hyperspectral images when querying informative unlabeled samples subject to certain acquisition heuristics. A major reason for this bias is that the acquisition heuristics are normally derived based on the output of a deep learning classifier, in which representational power is bounded by the number of labeled training samples at hand. To address this limitation, we developed a feature-oriented adversarial active learning (FAAL) strategy, which exploits the high-level features from one intermediate layer of a deep learning classifier for establishing an acquisition heuristic based on a generative adversarial network (GAN). Specifically, we developed a feature generator for generating fake high-level features and a feature discriminator for discriminating between the real high-level features and the fake ones. Trained with both the real and the fake high-level features, the feature discriminator comprehensively captures the feature variability of hyperspectral images and yields a powerful and generalized discriminative capability. We leverage the well-trained feature discriminator as the acquisition heuristic to measure the informativeness of unlabeled samples. Experimental results validate the effectiveness of both (i) the full FAAL framework and (ii) the adversarially learned acquisition heuristic, for the task of classifying hyperspectral images with limited labeled samples.

SEAL: Semisupervised Adversarial Active Learning on Attributed Graphs.

Active learning (AL) on attributed graphs has received increasing attention with the prevalence of graph-structured data. Although AL has been widely studied for alleviating label sparsity issues with the conventional nonrelational data, how to make it effective over attributed graphs remains an open research question. Existing AL algorithms on node classification attempt to reuse the classic AL query strategies designed for nonrelational data. However, they suffer from two major limitations. First, different AL query strategies calculated in distinct scoring spaces are often naively combined to determine which nodes to be labeled. Second, the AL query engine and the learning of the classifier are treated as two separating processes, resulting in unsatisfactory performance. In this article, we propose a SEmisupervised Adversarial active Learning (SEAL) framework on attributed graphs, which fully leverages the representation power of deep neural networks and devises a novel AL query strategy for node classification in an adversarial way. Our framework learns two adversarial components; a graph embedding network that encodes both the unlabeled and labeled nodes into a common latent space, expecting to trick the discriminator to regard all nodes as already labeled, and a semisupervised discriminator network that distinguishes the unlabeled from the existing labeled nodes. The divergence score, generated by the discriminator in a unified latent space, serves as the informativeness measure to actively select the most informative node to be labeled by an oracle. The two adversarial components form a closed loop to mutually and simultaneously reinforce each other toward enhancing the AL performance. Extensive experiments on real-world networks validate the effectiveness of the SEAL framework with superior performance improvements to state-of-the-art baselines on node classification tasks.

Adversarial active learning for the identification of medical concepts and annotation inconsistency.

Named entity recognition (NER) is a principal task in the biomedical field and deep learning-based algorithms have been widely applied to biomedical NER. However, all of these methods that are applied to biomedical corpora use only annotated samples to maximize their performances. Thus, (1) large numbers of unannotated samples are relinquished and their values are overlooked. (2) Compared with other types of active learning (AL) algorithms, generative adversarial learning (GAN)-based AL methods have developed slowly. Furthermore, current diversity-based AL methods only compute similarities between a pair of sentences and cannot evaluate distribution similarities between groups of sentences. Annotation inconsistency is one of the significant challenges in the biomedical annotation field. Most existing methods for addressing this challenge are statistics-based or rule-based methods. (3) They require sufficient expert knowledge and complex designs. To address challenges (1), (2), and (3) simultaneously, we propose innovative algorithms. GAN is introduced in this paper, and we propose the GAN-bidirectional long short-term memory-conditional random field (GAN-BiLSTM-CRF) and the GAN-bidirectional encoder representations from transformers-conditional random field (GAN-BERT-CRF) models, which can be considered an NER model, an AL model, and a model identifying error labels. BiLSTM-CRF or BERT-CRF is defined as the generator and a convolutional neural network (CNN)-based network is considered the discriminator. (1) The generator employs unannotated samples in addition to annotated samples to maximize NER performance. (2) The outputs of the CRF layer and the discriminator are used to select unlabeled samples for the AL task. (3) The discriminator discriminates the distribution of error labels from that of correct labels, identify error labels, and address the annotation inconsistency challenge. The corpus from the 2010 i2b2/VA NLP challenge and the Chinese CCKS-2017 Task 2 dataset are adopted for experiments. Compared to the baseline BiLSTM-CRF and BERT-CRF, the GAN-BiLSTM-CRF and GAN-BERT-CRF models achieved significant improvements on the precision, recall, and F1 scores in terms of NER performance. Learning curves in AL experiments show the comparative results of the proposed models. Furthermore, the trained discriminator can identify samples with incorrect medical labels in both simulation and real-word experimental environments. The idea of introducing GAN contributes significant results in terms of NER, active learning, and the ability to identify incorrect annotated samples. The benefits of GAN will be further studied.

Adversarial Active Learning for Named Entity Recognition in Cybersecurity

Owing to the continuous barrage of cyber threats, there is a massive amount of cyber threat intelligence. However, a great deal of cyber threat intelligence come from textual sources. For analysis of cyber threat intelligence, many security analysts rely on cumbersome and time-consuming manual efforts. Cybersecurity knowledge graph plays a significant role in automatics analysis of cyber threat intelligence. As the foundation for constructing cybersecurity knowledge graph, named entity recognition (NER) is required for identifying critical threat-related elements from textual cyber threat intelligence. Recently, deep neural network-based models have attained very good results in NER. However, the performance of these models relies heavily on the amount of labeled data. Since labeled data in cybersecurity is scarce, in this paper, we propose an adversarial active learning framework to effectively select the informative samples for further annotation. In addition, leveraging the long short-term memory (LSTM) network and the bidirectional LSTM (BiLSTM) network, we propose a novel NER model by introducing a dynamic attention mechanism into the BiLSTM-LSTM encoderdecoder. With the selected informative samples annotated, the proposed NER model is retrained. As a result, the performance of the NER model is incrementally enhanced with low labeling cost. Experimental results show the effectiveness of the proposed method.

Generative Adversarial Active Learning for Unsupervised Outlier Detection

Outlier detection is an important topic in machine learning and has been used in a wide range of applications. In this paper, we approach outlier detection as a binary-classification issue by sampling potential outliers from a uniform reference distribution. However, due to the sparsity of data in high-dimensional space, a limited number of potential outliers may fail to provide sufficient information to assist the classifier in describing a boundary that can separate outliers from normal data effectively. To address this, we propose a novel Single-Objective Generative Adversarial Active Learning (SO-GAAL) method for outlier detection, which can directly generate informative potential outliers based on the mini-max game between a generator and a discriminator. Moreover, to prevent the generator from falling into the mode collapsing problem, the stop node of training should be determined when SO-GAAL is able to provide sufficient information. But without any prior information, it is extremely difficult for SO-GAAL. Therefore, we expand the network structure of SO-GAAL from a single generator to multiple generators with different objectives (MO-GAAL), which can generate a reasonable reference distribution for the whole dataset. We empirically compare the proposed approach with several state-of-the-art outlier detection methods on both synthetic and real-world datasets. The results show that MO-GAAL outperforms its competitors in the majority of cases, especially for datasets with various cluster types or high irrelevant variable ratio.