Active semi-supervised learning based on self-expressive correlation with generative adversarial networks

Zhang, Xiaoyu; Shi, Haichao; Zhu, Xiaobin; Li, Peng

doi:10.1016/j.neucom.2019.01.083

Cited by 50 publications

(20 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The past decade has witnessed remarkable progress in machine learning on various practical applications [10][11][12][13][14][15][16][17], especially in fraudulent phone call recognition. Previous studies have shown that fraudulent phone calls can be effectively recognized through cognitive learning of the phone number features and call behavior features.…”

Section: Related Workmentioning

confidence: 99%

Automated Fraudulent Phone Call Recognition through Deep Learning

Xing

Wang

et al. 2020

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Several studies have shown that the phone number and call behavior generated by a phone call reveal the type of phone call. By analyzing the phone number rules and call behavior patterns, we can recognize the fraudulent phone call. The success of this recognition heavily depends on the particular set of features that are used to construct the classifier. Since these features are human-labor engineered, any change introduced to the telephone fraud can render these carefully constructed features ineffective. In this paper, we show that we can automate the feature engineering process and, thus, automatically recognize the fraudulent phone call by applying our proposed novel approach based on deep learning. We design and construct a new classifier based on Call Detail Records (CDR) for fraudulent phone call recognition and find that the performance achieved by our deep learning-based approach outperforms competing methods. Experimental results demonstrate the effectiveness of the proposed approach. Specifically, in our accuracy evaluation, the obtained accuracy exceeds 99%, and the most performant deep learning model is 4.7% more accurate than the state-of-the-art recognition model on average. Furthermore, we show that our deep learning approach is very stable in real-world environments, and the implicit features automatically learned by our approach are far more resilient to dynamic changes of a fraudulent phone number and its call behavior over time. We conclude that the ability to automatically construct the most relevant phone number features and call behavior features and perform accurate fraudulent phone call recognition makes our deep learning-based approach a precise, efficient, and robust technique for fraudulent phone call recognition.

show abstract

Section: Related Workmentioning

confidence: 99%

Automated Fraudulent Phone Call Recognition through Deep Learning

Xing

Wang

et al. 2020

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…Reference [32] trained a conditional variational autoencoder to learn the underlying probability distribution of the image features conditioned on the class embedding vector. Reference [5] proposed the algorithm of active semi-supervised learning with generative adversarial network to cope with issue of inadequate and unbalanced training data that has been obsessing model learning. Instead of generating image instances, [33] integrated Wasserstein generative adversarial network and multimodal embedding methods to synthesize CNN features conditioned on classlevel semantic information.…”

Section: Related Workmentioning

confidence: 99%

“…In recent years, with the development of supervised deep learning technology, large-scale classification for both samples and categories has received high attention [1]- [4]. Although the researches of semi-supervised learning and active learning, where only a few labels are needed, have achieved good performances [5]- [8], new class samples are likely to appear during testing, which may degrade the generalization performance of the learning models dramatically. However, human beings can understand and identify the classes even if no sample has been seen before, as long as the relevant characteristics are given.…”

Section: Introductionmentioning

confidence: 99%

Cross-Layer Autoencoder for Zero-Shot Learning

Zhang

Yang³

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Zero-shot learning (ZSL) is the task of recognizing samples from their related classes which have never been seen during model training. ZSL is generally realized through learning a common embedding space where both high dimensional visual features and some pre-defined semantics can be mapped. However, this kind of solutions usually suffers from domain shift. In addition, the limitation and subjectivity of manual semantic information can also affect the classification results. To address these challenges, this paper proposes a novel end-to-end deep learning model called Cross-Layer Autoencoder (CLAE), which integrates different ways of semantic mapping and maintains reconstruction information. Besides, a regularized loss function is used to preserve local class manifolds. Extensive experiments for both traditional and generalized ZSL tasks are conducted on several benchmark datasets, and high effectiveness of the proposed method and its superiority over many previous researches are demonstrated. INDEX TERMS Zero-shot learning, cross-layer autoencoder, regularized loss function, class manifolds.

show abstract

“…For example, it can elevate the measure accuracy of projects that are difficult to measure in construction engineering [1]; it can build the 3D models for historical buildings to record information in terms of cultural relics; it can detect underwater distances to provide data for environmental protection programs [2]; it also can be used to detect landslides and other disasters [3]. In recent years, deep learning has developed rapidly and has achieved remarkable results in various fields [4][5][6][7]. Therefore, this article also uses deep learning algorithms for pixel-level classification of LiDAR data.…”

Section: Introductionmentioning

confidence: 99%

A Novel LiDAR Data Classification Algorithm Combined CapsNet with ResNet

Wang

et al. 2020

Sensors

View full text Add to dashboard Cite

LiDAR data contain feature information such as the height and shape of the ground target and play an important role for land classification. The effect of convolutional neural network (CNN) for feature extraction on LiDAR data is very significant, however CNN cannot resolve the spatial relationship of features adequately. The capsule network (CapsNet) can identify the spatial variations of features and is widely used in supervised learning. In this article, the CapsNet is combined with the residual network (ResNet) to design a deep network-ResCapNet for improving the accuracy of LiDAR classification. The capsule network represents the features by vectors, which can account for the direction of the features and the relative position between the features. Therefore, more detailed feature information can be extracted. ResNet protects the integrity of information by passing input information to the output directly, which can solve the problem of network degradation caused by information loss in the traditional CNN propagation process to a certain extent. Two different LiDAR data sets and several classic machine learning algorithms are used for comparative experiments. The experimental results show that ResCapNet proposed in this article `improve the performance of LiDAR classification.

show abstract

Active semi-supervised learning based on self-expressive correlation with generative adversarial networks

Cited by 50 publications

References 20 publications

Automated Fraudulent Phone Call Recognition through Deep Learning

Automated Fraudulent Phone Call Recognition through Deep Learning

Cross-Layer Autoencoder for Zero-Shot Learning

A Novel LiDAR Data Classification Algorithm Combined CapsNet with ResNet

Contact Info

Product

Resources

About