Showing papers by "Beijing University of Posts and Telecommunications published in 2020"

Graph Neural Networks: A Review of Methods and Applications

Abstract: Lots of learning tasks require dealing with graph data which contains rich relation information among elements. Modeling physics systems, learning molecular fingerprints, predicting protein interface, and classifying diseases demand a model to learn from graph inputs. In other domains such as learning from non-structural data like texts and images, reasoning on extracted structures (like the dependency trees of sentences and the scene graphs of images) is an important research topic which also needs graph reasoning models. Graph neural networks (GNNs) are neural models that capture the dependence of graphs via message passing between the nodes of graphs. In recent years, variants of GNNs such as graph convolutional network (GCN), graph attention network (GAT), graph recurrent network (GRN) have demonstrated ground-breaking performances on many deep learning tasks. In this survey, we propose a general design pipeline for GNN models and discuss the variants of each component, systematically categorize the applications, and propose four open problems for future research.

Blockchain and Federated Learning for Privacy-Preserved Data Sharing in Industrial IoT

Abstract: The rapid increase in the volume of data generated from connected devices in industrial Internet of Things paradigm, opens up new possibilities for enhancing the quality of service for the emerging applications through data sharing. However, security and privacy concerns (e.g., data leakage) are major obstacles for data providers to share their data in wireless networks. The leakage of private data can lead to serious issues beyond financial loss for the providers. In this article, we first design a blockchain empowered secure data sharing architecture for distributed multiple parties. Then, we formulate the data sharing problem into a machine-learning problem by incorporating privacy-preserved federated learning. The privacy of data is well-maintained by sharing the data model instead of revealing the actual data. Finally, we integrate federated learning in the consensus process of permissioned blockchain, so that the computing work for consensus can also be used for federated training. Numerical results derived from real-world datasets show that the proposed data sharing scheme achieves good accuracy, high efficiency, and enhanced security.

Deep Facial Expression Recognition: A Survey

Abstract: With the transition of facial expression recognition (FER) from laboratory-controlled to in-the-wild conditions and the recent success of deep learning in various fields, deep neural networks have increasingly been leveraged to learn discriminative representations for automatic FER. Recent deep FER systems generally focus on two important issues: overfitting caused by a lack of sufficient training data and expression-unrelated variations, such as illumination, head pose and identity bias. In this survey, we provide a comprehensive review on deep FER, including datasets and algorithms that provide insights into these problems. First, we introduce available datasets that are widely used and provide data selection and evaluation principles. We then describe the standard pipeline of a deep FER system with related background knowledge and suggestions of applicable implementations. For the state of the art in deep FER, we introduce existing deep networks and training strategies that are designed for FER, and discuss their advantages and limitations. Competitive performances and experimental comparisons on widely used benchmarks are also summarized. We then extend our survey to additional related issues and application scenarios. Finally, we review the remaining challenges and opportunities in this field as well as future directions for the design of robust deep FER system.

Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Selection

Abstract: Object detection has been dominated by anchor-based detectors for several years. Recently, anchor-free detectors have become popular due to the proposal of FPN and Focal Loss. In this paper, we first point out that the essential difference between anchor-based and anchor-free detection is actually how to define positive and negative training samples, which leads to the performance gap between them. If they adopt the same definition of positive and negative samples during training, there is no obvious difference in the final performance, no matter regressing from a box or a point. This shows that how to select positive and negative training samples is important for current object detectors. Then, we propose an Adaptive Training Sample Selection (ATSS) to automatically select positive and negative samples according to statistical characteristics of object. It significantly improves the performance of anchor-based and anchor-free detectors and bridges the gap between them. Finally, we discuss the necessity of tiling multiple anchors per location on the image to detect objects. Extensive experiments conducted on MS COCO support our aforementioned analysis and conclusions. With the newly introduced ATSS, we improve state-of-the-art detectors by a large margin to 50.7% AP without introducing any overhead. The code is available at https://github.com/sfzhang15/ATSS.

Blockchain Empowered Asynchronous Federated Learning for Secure Data Sharing in Internet of Vehicles

Abstract: In Internet of Vehicles (IoV), data sharing among vehicles for collaborative analysis can improve the driving experience and service quality. However, the bandwidth, security and privacy issues hinder data providers from participating in the data sharing process. In addition, due to the intermittent and unreliable communications in IoV, the reliability and efficiency of data sharing need to be further enhanced. In this paper, we propose a new architecture based on federated learning to relieve transmission load and address privacy concerns of providers. To enhance the security and reliability of model parameters, we develop a hybrid blockchain architecture which consists of the permissioned blockchain and the local Directed Acyclic Graph (DAG). Moreover, we propose an asynchronous federated learning scheme by adopting Deep Reinforcement Learning (DRL) for node selection to improve the efficiency. The reliability of shared data is also guaranteed by integrating learned models into blockchain and executing a two-stage verification. Numerical results show that the proposed data sharing scheme provides both higher learning accuracy and faster convergence.

Exploiting Intelligent Reflecting Surfaces in NOMA Networks: Joint Beamforming Optimization

Abstract: This paper investigates a downlink multiple-input single-output intelligent reflecting surface (IRS) aided non-orthogonal multiple access (NOMA) system, where a base station (BS) serves multiple users with the aid of IRSs. Our goal is to maximize the sum rate of all users by jointly optimizing the active beamforming at the BS and the passive beamforming at the IRS, subject to successive interference cancellation decoding rate conditions and IRS reflecting elements constraints. In term of the characteristics of reflection amplitudes and phase shifts, we consider ideal and non-ideal IRS assumptions. To tackle the formulated non-convex problems, we propose efficient algorithms by invoking alternating optimization, which design the active beamforming and passive beamforming alternately. For the ideal IRS scenario, the two subproblems are solved by invoking the successive convex approximation technique. For the non-ideal IRS scenario, constant modulus IRS elements are further divided into continuous phase shifts and discrete phase shifts. To tackle the passive beamforming problem with continuous phase shifts, a novel algorithm is developed by utilizing the sequential rank-one constraint relaxation approach, which is guaranteed to find a locally optimal rank-one solution. Then, a quantization-based scheme is proposed for discrete phase shifts. Finally, numerical results illustrate that: i) the system sum rate can be significantly improved by deploying the IRS with the proposed algorithms; ii) 3-bit phase shifters are capable of achieving almost the same performance as the ideal IRS; iii) the proposed IRS-aided NOMA systems achieve higher system sum rate than the IRS-aided orthogonal multiple access system.

Reconfigurable Intelligent Surfaces: Principles and Opportunities

Abstract: Reconfigurable intelligent surfaces (RISs), also known as intelligent reflecting surfaces (IRSs), have received significant attention for their potential to enhance the capacity and coverage of wireless networks by smartly reconfiguring the wireless propagation environment. Therefore, RISs are considered a promising technology for the sixth-generation (6G) communication networks. In this context, we provide a comprehensive overview of the state-of-the-art on RISs, with focus on their operating principles, performance evaluation, beamforming design and resource management, applications of machine learning to RIS-enhanced wireless networks, as well as the integration of RISs with other emerging technologies. We describe the basic principles of RISs both from physics and communications perspectives, based on which we present performance evaluation of multi-antenna assisted RIS systems. In addition, we systematically survey existing designs for RIS-enhanced wireless networks encompassing performance analysis, information theory, and performance optimization perspectives. Furthermore, we survey existing research contributions that apply machine learning for tackling challenges in dynamic scenarios, such as random fluctuations of wireless channels and user mobility in RIS-enhanced wireless networks. Last but not least, we identify major issues and research opportunities associated with the integration of RISs and other emerging technologies for application to next-generation networks.

Toward Edge Intelligence: Multiaccess Edge Computing for 5G and Internet of Things

Abstract: To satisfy the increasing demand of mobile data traffic and meet the stringent requirements of the emerging Internet-of-Things (IoT) applications such as smart city, healthcare, and augmented/virtual reality (AR/VR), the fifth-generation (5G) enabling technologies are proposed and utilized in networks As an emerging key technology of 5G and a key enabler of IoT, multiaccess edge computing (MEC), which integrates telecommunication and IT services, offers cloud computing capabilities at the edge of the radio access network (RAN) By providing computational and storage resources at the edge, MEC can reduce latency for end users Hence, this article investigates MEC for 5G and IoT comprehensively It analyzes the main features of MEC in the context of 5G and IoT and presents several fundamental key technologies which enable MEC to be applied in 5G and IoT, such as cloud computing, software-defined networking/network function virtualization, information-centric networks, virtual machine (VM) and containers, smart devices, network slicing, and computation offloading In addition, this article provides an overview of the role of MEC in 5G and IoT, bringing light into the different MEC-enabled 5G and IoT applications as well as the promising future directions of integrating MEC with 5G and IoT Moreover, this article further elaborates research challenges and open issues of MEC for 5G and IoT Last but not least, we propose a use case that utilizes MEC to achieve edge intelligence in IoT scenarios

Forward and Backward Information Retention for Accurate Binary Neural Networks

Abstract: Weight and activation binarization is an effective approach to deep neural network compression and can accelerate the inference by leveraging bitwise operations. Although many binarization methods have improved the accuracy of the model by minimizing the quantization error in forward propagation, there remains a noticeable performance gap between the binarized model and the full-precision one. Our empirical study indicates that the quantization brings information loss in both forward and backward propagation, which is the bottleneck of training accurate binary neural networks. To address these issues, we propose an Information Retention Network (IR-Net) to retain the information that consists in the forward activations and backward gradients. IR-Net mainly relies on two technical contributions: (1) Libra Parameter Binarization (Libra-PB): simultaneously minimizing both quantization error and information loss of parameters by balanced and standardized weights in forward propagation; (2) Error Decay Estimator (EDE): minimizing the information loss of gradients by gradually approximating the sign function in backward propagation, jointly considering the updating ability and accurate gradients. We are the first to investigate both forward and backward processes of binary networks from the unified information perspective, which provides new insight into the mechanism of network binarization. Comprehensive experiments with various network structures on CIFAR-10 and ImageNet datasets manifest that the proposed IR-Net can consistently outperform state-of-the-art quantization methods.

AM-GCN: Adaptive Multi-channel Graph Convolutional Networks

Abstract: Graph Convolutional Networks (GCNs) have gained great popularity in tackling various analytics tasks on graph and network data. However, some recent studies raise concerns about whether GCNs can optimally integrate node features and topological structures in a complex graph with rich information. In this paper, we first present an experimental investigation. Surprisingly, our experimental results clearly show that the capability of the state-of-the-art GCNs in fusing node features and topological structures is distant from optimal or even satisfactory. The weakness may severely hinder the capability of GCNs in some classification tasks, since GCNs may not be able to adaptively learn some deep correlation information between topological structures and node features. Can we remedy the weakness and design a new type of GCNs that can retain the advantages of the state-of-the-art GCNs and, at the same time, enhance the capability of fusing topological structures and node features substantially? We tackle the challenge and propose an adaptive multi-channel graph convolutional networks for semi-supervised classification (AM-GCN). The central idea is that we extract the specific and common embeddings from node features, topological structures, and their combinations simultaneously, and use the attention mechanism to learn adaptive importance weights of the embeddings. Our extensive experiments on benchmark data sets clearly show that AM-GCN extracts the most correlated information from both node features and topological structures substantially, and improves the classification accuracy with a clear margin.

A Multi-Organ Nucleus Segmentation Challenge

Abstract: Generalized nucleus segmentation techniques can contribute greatly to reducing the time to develop and validate visual biomarkers for new digital pathology datasets. We summarize the results of MoNuSeg 2018 Challenge whose objective was to develop generalizable nuclei segmentation techniques in digital pathology. The challenge was an official satellite event of the MICCAI 2018 conference in which 32 teams with more than 80 participants from geographically diverse institutes participated. Contestants were given a training set with 30 images from seven organs with annotations of 21,623 individual nuclei. A test dataset with 14 images taken from seven organs, including two organs that did not appear in the training set was released without annotations. Entries were evaluated based on average aggregated Jaccard index (AJI) on the test set to prioritize accurate instance segmentation as opposed to mere semantic segmentation. More than half the teams that completed the challenge outperformed a previous baseline. Among the trends observed that contributed to increased accuracy were the use of color normalization as well as heavy data augmentation. Additionally, fully convolutional networks inspired by variants of U-Net, FCN, and Mask-RCNN were popularly used, typically based on ResNet or VGG base architectures. Watershed segmentation on predicted semantic segmentation maps was a popular post-processing strategy. Several of the top techniques compared favorably to an individual human annotator and can be used with confidence for nuclear morphometrics.

Differentially Private Asynchronous Federated Learning for Mobile Edge Computing in Urban Informatics

Abstract: Driven by technologies such as mobile edge computing and 5G, recent years have witnessed the rapid development of urban informatics, where a large amount of data is generated. To cope with the growing data, artificial intelligence algorithms have been widely exploited. Federated learning is a promising paradigm for distributed edge computing, which enables edge nodes to train models locally without transmitting their data to a server. However, the security and privacy concerns of federated learning hinder its wide deployment in urban applications such as vehicular networks. In this article, we propose a differentially private asynchronous federated learning scheme for resource sharing in vehicular networks. To build a secure and robust federated learning scheme, we incorporate local differential privacy into federated learning for protecting the privacy of updated local models. We further propose a random distributed update scheme to get rid of the security threats led by a centralized curator. Moreover, we perform the convergence boosting in our proposed scheme by updates verification and weighted aggregation. We evaluate our scheme on three real-world datasets. Numerical results show the high accuracy and efficiency of our proposed scheme, whereas preserve the data privacy.

A Vision of C-V2X: Technologies, Field Testing, and Challenges With Chinese Development

Abstract: Cellular vehicle-to-everything (C-V2X) is an important enabling technology for autonomous driving and intelligent transportation systems. It evolves from long-term evolution (LTE)-V2X to new radio (NR)-V2X, which will coexist and be complementary with each other to provide low-latency, high-reliability, and high-throughput communications for various C-V2X applications. In this article, a vision of C-V2X is presented. The requirements of the basic road safety and advanced applications, the architecture, the key technologies, and the standards of C-V2X are introduced, highlighting the technical evolution path from LTE-V2X to NR-V2X. Especially, based on the continual and active promotion of C-V2X research, field testing, and development in China, the related works and progresses are also presented. Finally, the trends of C-V2X applications with technical challenges are envisioned.

Structural Deep Clustering Network

Abstract: Clustering is a fundamental task in data analysis. Recently, deep clustering, which derives inspiration primarily from deep learning approaches, achieves state-of-the-art performance and has attracted considerable attention. Current deep clustering methods usually boost the clustering results by means of the powerful representation ability of deep learning, e.g., autoencoder, suggesting that learning an effective representation for clustering is a crucial requirement. The strength of deep clustering methods is to extract the useful representations from the data itself, rather than the structure of data, which receives scarce attention in representation learning. Motivated by the great success of Graph Convolutional Network (GCN) in encoding the graph structure, we propose a Structural Deep Clustering Network (SDCN) to integrate the structural information into deep clustering. Specifically, we design a delivery operator to transfer the representations learned by autoencoder to the corresponding GCN layer, and a dual self-supervised mechanism to unify these two different deep neural architectures and guide the update of the whole model. In this way, the multiple structures of data, from low-order to high-order, are naturally combined with the multiple representations learned by autoencoder. Furthermore, we theoretically analyze the delivery operator, i.e., with the delivery operator, GCN improves the autoencoder-specific representation as a high-order graph regularization constraint and autoencoder helps alleviate the over-smoothing problem in GCN. Through comprehensive experiments, we demonstrate that our propose model can consistently perform better over the state-of-the-art techniques.

Online Knowledge Distillation via Collaborative Learning

Abstract: This work presents an efficient yet effective online Knowledge Distillation method via Collaborative Learning, termed KDCL, which is able to consistently improve the generalization ability of deep neural networks (DNNs) that have different learning capacities. Unlike existing two-stage knowledge distillation approaches that pre-train a DNN with large capacity as the ''teacher'' and then transfer the teacher's knowledge to another ''student'' DNN unidirectionally (i.e. one-way), KDCL treats all DNNs as ''students'' and collaboratively trains them in a single stage (knowledge is transferred among arbitrary students during collaborative training), enabling parallel computing, fast computations, and appealing generalization ability. Specifically, we carefully design multiple methods to generate soft target as supervisions by effectively ensembling predictions of students and distorting the input images. Extensive experiments show that KDCL consistently improves all the ''students'' on different datasets, including CIFAR-100 and ImageNet. For example, when trained together by using KDCL, ResNet-50 and MobileNetV2 achieve 78.2% and 74.0% top-1 accuracy on ImageNet, outperforming the original results by 1.4% and 2.0% respectively. We also verify that models pre-trained with KDCL transfer well to object detection and semantic segmentation on MS COCO dataset. For instance, the FPN detector is improved by 0.9% mAP.

Multi-UAV-Enabled Load-Balance Mobile-Edge Computing for IoT Networks

Abstract: Unmanned aerial vehicles (UAVs) have been widely used to provide enhanced information coverage as well as relay services for ground Internet-of-Things (IoT) networks. Considering the substantially limited processing capability, the IoT devices may not be able to tackle with heavy computing tasks. In this article, a multi-UAV-aided mobile-edge computing (MEC) system is constructed, where multiple UAVs act as MEC nodes in order to provide computing offloading services for ground IoT nodes which have limited local computing capabilities. For the sake of balancing the load for UAVs, the differential evolution (DE)-based multi-UAV deployment mechanism is proposed, where we model the access problem as a generalized assignment problem (GAP), which is then solved by a near-optimal solution algorithm. Based on this, we are capable of achieving the load balance of these drones while guaranteeing the coverage constraint and satisfying the quality of service (QoS) of IoT nodes. Furthermore, a deep reinforcement learning (DRL) algorithm is conceived for the task scheduling in a certain UAV, which improves the efficiency of the task execution in each UAV. Finally, sufficient simulation results show the feasibility and superiority of our proposed load-balance-oriented UAV deployment scheme as well as the task scheduling algorithm.

Vision, Requirements, and Technology Trend of 6G: How to Tackle the Challenges of System Coverage, Capacity,User Data-Rate and Movement Speed

Abstract: Since 5G new radio comes with non-standalone (NSA) and standalone (SA) versions in 3GPP, research on 6G has been on schedule by academics and industries. Though 6G is supposed to have much higher capabilities than 5G, yet there is no clear description about what 6G is. In this article, a comprehensive discussion of 6G is given based on the review of 5G developments, covering visions and requirements, technology trends and challenges, aiming at tackling the challenge of coverage, capacity, the user data rate and movement speed of mobile communication system. The vision of 6G is to fully support the development of a Ubiquitous Intelligent Mobile Society with intelligent life and industries. Finally, the roadmap of the 6G standard is suggested for the future.

Long-Distance Continuous-Variable Quantum Key Distribution over 202.81 km of Fiber.

Abstract: Quantum key distribution provides secure keys resistant to code-breaking quantum computers. The continuous-variable version of quantum key distribution offers the advantages of higher secret key rates in metropolitan areas, as well as the use of standard telecom components that can operate at room temperature. However, the transmission distance of these systems (compared with discrete-variable systems) are currently limited and considered unsuitable for long-distance distribution. Herein, we report the experimental results of long distance continuous-variable quantum key distribution over 202.81 km of ultralow-loss optical fiber by suitably controlling the excess noise and employing highly efficient reconciliation procedures. This record-breaking implementation of the continuous-variable quantum key distribution doubles the previous distance record and shows the road for long-distance and large-scale secure quantum key distribution using room-temperature standard telecom components.

The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification

Abstract: The key to solving fine-grained image categorization is finding discriminate and local regions that correspond to subtle visual traits. Great strides have been made, with complex networks designed specifically to learn part-level discriminate feature representations. In this paper, we show that it is possible to cultivate subtle details without the need for overly complicated network designs or training mechanisms – a single loss is all it takes. The main trick lies with how we delve into individual feature channels early on, as opposed to the convention of starting from a consolidated feature map. The proposed loss function, termed as mutual-channel loss (MC-Loss), consists of two channel-specific components: a discriminality component and a diversity component. The discriminality component forces all feature channels belonging to the same class to be discriminative, through a novel channel-wise attention mechanism. The diversity component additionally constraints channels so that they become mutually exclusive across the spatial dimension. The end result is therefore a set of feature channels, each of which reflects different locally discriminative regions for a specific class. The MC-Loss can be trained end-to-end, without the need for any bounding-box/part annotations, and yields highly discriminative regions during inference. Experimental results show our MC-Loss when implemented on top of common base networks can achieve state-of-the-art performance on all four fine-grained categorization datasets (CUB-Birds, FGVC-Aircraft, Flowers-102, and Stanford Cars). Ablative studies further demonstrate the superiority of the MC-Loss when compared with other recently proposed general-purpose losses for visual classification, on two different base networks. Codes are available at: https://github.com/dongliangchang/Mutual-Channel-Loss .

Instance Adaptive Self-training for Unsupervised Domain Adaptation

Abstract: The divergence between labeled training data and unlabeled testing data is a significant challenge for recent deep learning models. Unsupervised domain adaptation (UDA) attempts to solve such a problem. Recent works show that self-training is a powerful approach to UDA. However, existing methods have difficulty in balancing scalability and performance. In this paper, we propose an instance adaptive self-training framework for UDA on the task of semantic segmentation. To effectively improve the quality of pseudo-labels, we develop a novel pseudo-label generation strategy with an instance adaptive selector. Besides, we propose the region-guided regularization to smooth the pseudo-label region and sharpen the non-pseudo-label region. Our method is so concise and efficient that it is easy to be generalized to other unsupervised domain adaptation methods. Experiments on ‘GTA5 to Cityscapes’ and ‘SYNTHIA to Cityscapes’ demonstrate the superior performance of our approach compared with the state-of-the-art methods.

Joint radar and communication: A survey

Abstract: Joint radar and communication (JRC) technology has become important for civil and military applications for decades. This paper introduces the concepts, characteristics and advantages of JRC technology, presenting the typical applications that have benefited from JRC technology currently and in the future. This paper explores the state-of-the-art of JRC in the levels of coexistence, cooperation, co-design and collaboration. Compared to previous surveys, this paper reviews the entire trends that drive the development of radar sensing and wireless communication using JRC. Specifically, we explore an open research issue on radar and communication operating with mutual benefits based on collaboration, which represents the fourth stage of JRC evolution. This paper provides useful perspectives for future researches of JRC technology.

Meta-learning on Heterogeneous Information Networks for Cold-start Recommendation

Abstract: Cold-start recommendation has been a challenging problem due to sparse user-item interactions for new users or items. Existing efforts have alleviated the cold-start issue to some extent, most of which approach the problem at the data level. Earlier methods often incorporate auxiliary data as user or item features, while more recent methods leverage heterogeneous information networks (HIN) to capture richer semantics via higher-order graph structures. On the other hand, recent meta-learning paradigm sheds light on addressing cold-start recommendation at the model level, given its ability to rapidly adapt to new tasks with scarce labeled data, or in the context of cold-start recommendation, new users and items with very few interactions. Thus, we are inspired to develop a novel meta-learning approach named MetaHIN to address cold-start recommendation on HINs, to exploit the power of meta-learning at the model level and HINs at the data level simultaneously. The solution is non-trivial, for how to capture HIN-based semantics in the meta-learning setting, and how to learn the general knowledge that can be easily adapted to multifaceted semantics, remain open questions. In MetaHIN, we propose a novel semantic-enhanced tasks constructor and a co-adaptation meta-learner to address the two questions. Extensive experiments demonstrate that MetaHIN significantly outperforms the state of the arts in various cold-start scenarios. (Code and dataset are available at https://github.com/rootlu/MetaHIN.)

Joint Computation and Communication Design for UAV-Assisted Mobile Edge Computing in IoT

Abstract: Unmanned aerial vehicle (UAV)-assisted mobile edge computing (MEC) system is a prominent concept, where a UAV equipped with an MEC server is deployed to serve a number of terminal devices (TDs) of Internet of Things in a finite period. In this article, each TD has a certain latency-critical computation task in each time slot to complete. Three computation strategies can be available to each TD. First, each TD can operate local computing by itself. Second, each TD can partially offload task bits to the UAV for computing. Third, each TD can choose to offload task bits to access point via UAV relaying. We propose a new optimization problem formulation that aims to minimize the total energy consumption including communication-related energy, computation-related energy and UAV’s flight energy by optimizing the bits allocation, time slot scheduling, and power allocation as well as UAV trajectory design. As the formulated problem is nonconvex and difficult to find the optimal solution, we propose to solve the problem by two parts, and obtain the near optimal solution by the Lagrangian duality method and successive convex approximation technique, respectively. By analysis, the proposed algorithm can be guaranteed to converge within a dozen of iterations. Finally, numerical results are given to validate the proposed algorithm, which is verified to be efficient and superior to the other benchmark cases.

Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters

Abstract: Graph Neural Networks (GNNs) have been widely applied to fraud detection problems in recent years, revealing the suspiciousness of nodes by aggregating their neighborhood information via different relations However, few prior works have noticed the camouflage behavior of fraudsters, which could hamper the performance of GNN-based fraud detectors during the aggregation process In this paper, we introduce two types of camouflages based on recent empirical studies, ie, the feature camouflage and the relation camouflage Existing GNNs have not addressed these two camouflages, which results in their poor performance in fraud detection problems Alternatively, we propose a new model named CAmouflage-REsistant GNN (CARE-GNN), to enhance the GNN aggregation process with three unique modules against camouflages Concretely, we first devise a label-aware similarity measure to find informative neighboring nodes Then, we leverage reinforcement learning (RL) to find the optimal amounts of neighbors to be selected Finally, the selected neighbors across different relations are aggregated together Comprehensive experiments on two real-world fraud datasets demonstrate the effectiveness of the RL algorithm The proposed CARE-GNN also outperforms state-of-the-art GNNs and GNN-based fraud detectors We integrate all GNN-based fraud detectors as an opensource toolbox: this https URL The CARE-GNN code and datasets are available at this https URL

Structural Deep Clustering Network

Abstract: Clustering is a fundamental task in data analysis. Recently, deep clustering, which derives inspiration primarily from deep learning approaches, achieves state-of-the-art performance and has attracted considerable attention. Current deep clustering methods usually boost the clustering results by means of the powerful representation ability of deep learning, e.g., autoencoder, suggesting that learning an effective representation for clustering is a crucial requirement. The strength of deep clustering methods is to extract the useful representations from the data itself, rather than the structure of data, which receives scarce attention in representation learning. Motivated by the great success of Graph Convolutional Network (GCN) in encoding the graph structure, we propose a Structural Deep Clustering Network (SDCN) to integrate the structural information into deep clustering. Specifically, we design a delivery operator to transfer the representations learned by autoencoder to the corresponding GCN layer, and a dual self-supervised mechanism to unify these two different deep neural architectures and guide the update of the whole model. In this way, the multiple structures of data, from low-order to high-order, are naturally combined with the multiple representations learned by autoencoder. Furthermore, we theoretically analyze the delivery operator, i.e., with the delivery operator, GCN improves the autoencoder-specific representation as a high-order graph regularization constraint and autoencoder helps alleviate the over-smoothing problem in GCN. Through comprehensive experiments, we demonstrate that our propose model can consistently perform better over the state-of-the-art techniques.

A Review of Android Malware Detection Approaches Based on Machine Learning

Abstract: Android applications are developing rapidly across the mobile ecosystem, but Android malware is also emerging in an endless stream. Many researchers have studied the problem of Android malware detection and have put forward theories and methods from different perspectives. Existing research suggests that machine learning is an effective and promising way to detect Android malware. Notwithstanding, there exist reviews that have surveyed different issues related to Android malware detection based on machine learning. We believe our work complements the previous reviews by surveying a wider range of aspects of the topic. This paper presents a comprehensive survey of Android malware detection approaches based on machine learning. We briefly introduce some background on Android applications, including the Android system architecture, security mechanisms, and classification of Android malware. Then, taking machine learning as the focus, we analyze and summarize the research status from key perspectives such as sample acquisition, data preprocessing, feature selection, machine learning models, algorithms, and the evaluation of detection effectiveness. Finally, we assess the future prospects for research into Android malware detection based on machine learning. This review will help academics gain a full picture of Android malware detection based on machine learning. It could then serve as a basis for subsequent researchers to start new work and help to guide research in the field more generally.