检索结果-内蒙古大学图书馆

Hyperbolic multiplex network embedding with maps of random walk

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Sun, Peiyuan Li, Jianxin Beijing Advanced Institution on Big Data and Brain Computing Beihang University Beijing China

Recent research on network embedding in hyperbolic space have proven successful in several applications. However, nodes in real world networks tend to interact through several distinct channels. Simple aggregation or ignorance of this multiplexity will lead to misleading results. On the other hand, there exists redundant information between different interaction patterns between nodes. Recent research reveals the analogy between the community structure and the hyperbolic coordinate. To learn each node's effective embedding representation while reducing the redundancy of multiplex network, we then propose a unified framework combing multiplex network hyperbolic embedding and multiplex community detection. The intuitive rationale is that high order node embedding approach is expected to alleviate the observed network's sparse and noisy structure which will benefit the community detection task. On the contrary, the improved community structure will also guide the node embedding task. To incorporate the common features between channels while preserving unique features, a random walk approach which traversing in latent multiplex hyperbolic space is proposed to detect the community across channels and bridge the connection between node embedding and community detection. The proposed framework is evaluated on several network tasks using different real world dataset. The results demonstrates that our framework is effective and efficiency compared with state-of-the-art approaches. Copyright © 2019, The Authors. All rights reserved.

关键词： Network embeddings

Higher-Order Attribute-Enhancing Heterogeneous Graph Neural Networks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Jianxin Peng, Hao Cao, Yuwei Dou, Yingtong Zhang, Hekai Yu, Philip S. He, Lifang Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100083 China the Department of Computer Science University of Illinois at Chicago ChicagoIL60607 United States School of Information Science and Engineering Yanshan University Qinhuangdao066004 China the Department of Computer Science and Engineering Lehigh University BethlehemPA18015 United States

Graph neural networks (GNNs) have been widely used in deep learning on graphs. They can learn effective node representations that achieve superior performances in graph analysis tasks such as node classification and node clustering. However, most methods ignore the heterogeneity in real-world graphs. Methods designed for heterogeneous graphs, on the other hand, fail to learn complex semantic representations because they only use meta-paths instead of meta-graphs. Furthermore, they cannot fully capture the content-based correlations between nodes, as they either do not use the self-attention mechanism or only use it to consider the immediate neighbors of each node, ignoring the higher-order neighbors. We propose a novel Higher-order Attribute-Enhancing (HAE) framework that enhances node embedding in a layer-by-layer manner. Under the HAE framework, we propose a Higher-order Attribute-Enhancing Graph Neural Network (HAEGNN) for heterogeneous network representation learning. HAEGNN simultaneously incorporates meta-paths and meta-graphs for rich, heterogeneous semantics, and leverages the self-attention mechanism to explore content-based nodes’ interactions. The unique higher-order architecture of HAEGNN allows examining the first-order as well as higher-order neighborhoods. Moreover, HAEGNN shows good explainability as it learns the importances of different meta-paths and meta-graphs. HAEGNN is also memory-efficient, for it avoids per meta-path based matrix calculation. Experimental results not only show HAEGNN’s superior performance against the state-of-the-art methods in node classification, node clustering, and visualization, but also demonstrate its superiorities in terms of memory efficiency and explainability. © 2021, CC BY.

关键词： Graph neural networks

Towards Graph Self-Supervised Learning with Contrastive Adjusted Zooming

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zheng, Yizhen Jin, Ming Pan, Shirui Li, Yuan-Fang Peng, Hao Li, Ming Li, Zhao Department of Data Science and AI Faculty of IT Monash University ClaytonVIC3800 Australia School of Information and Communication Technology Griffith University Australia SouthportQLD4222 Australia Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China Key Laboratory of Intelligent Education Technology Application of Zhejiang Province Zhejiang Normal University Jinhua321004 China Alibaba Group Hangzhou311100 China

Graph representation learning (GRL) is critical for graph-structured data analysis. However, most of the existing graph neural networks (GNNs) heavily rely on labeling information, which is normally expensive to obtain in the real world. Although some existing works aim to effectively learn graph representations in an unsupervised manner, they suffer from certain limitations, such as the heavy reliance on monotone contrastiveness and limited scalability. To overcome the aforementioned problems, in light of the recent advancements in graph contrastive learning, we introduce a novel self-supervised graph representation learning algorithm via Graph Contrastive Adjusted Zooming, namely G-Zoom, to learn node representations by leveraging the proposed adjusted zooming scheme. Specifically, this mechanism enables G-Zoom to explore and extract self-supervision signals from a graph from multiple scales: micro (i.e., node-level), meso (i.e., neighborhood-level), and macro (i.e., subgraph-level). Firstly, we generate two augmented views of the input graph via two different graph augmentations. Then, we establish three different contrastiveness on the above three scales progressively, from node, neighboring, to subgraph level, where we maximize the agreement between graph representations across scales. While we can extract valuable clues from a given graph on the micro and macro perspectives, the neighboring-level contrastiveness offers G-Zoom the capability of a customizable option based on our adjusted zooming scheme to manually choose an optimal viewpoint that lies between the micro and macro perspectives to better understand the graph data. Additionally, to make our model scalable to large graphs, we employ a parallel graph diffusion approach to decouple model training from the graph size. We have conducted extensive experiments on real-world datasets, and the results demonstrate that our proposed model outperforms state-of-the-art methods consistently. © 2021, CC BY.

关键词： Graph neural networks

Behavior variations and their implications for popularity promotions: From elites to mass in Weibo

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Shi, Bowen Xu, Ke Zhao, Jichang State Key Lab of Software Development Environment Beihang University Beijing China School of Economics and Management Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing China

The boom in social media with regard to producing and consuming information simultaneously implies the crucial role of online user influence in determining content popularity. In particular, understanding behavior variations between the influential elites and the mass grassroots is an important issue in communication. However, how their behavior varies across user categories and content domains, and how these differences influence content popularity are rarely addressed. From a novel view of seven content-domains, a detailed picture of behavior variations among five user groups, from both views of elites and mass, is drawn in Weibo, one of the most popular Twitter-like services in China. Interestingly, elites post more diverse contents with video links while the mass possess retweeters of higher loyalty. According to these variations, user-oriented actions of enhancing content popularity are discussed and testified. The most surprising finding is that the diversity of contents do not always bring more retweets, and the mass and elites should promote content popularity by increasing their retweeter counts and loyalty, respectively. Our results for the first time demonstrate the possibility of highly individualized strategies of popularity promotions in social media, instead of a universal principle. Keywords: Social media, User behavior, Elites, Mass, User influence, Popularity promotion Copyright © 2020, The Authors. All rights reserved.

关键词： Social networking (online)

Cross-domain object detection through coarse-to-fine feature adaptation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zheng, Yangtao Huang, Di Liu, Songtao Wang, Yunhong Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University State Key Laboratory of Software Development Environment Beihang University School of Computer Science and Engineering Beihang University Beijing100191 China

Recent years have witnessed great progress in deep learning based object detection. However, due to the domain shift problem, applying off-the-shelf detectors to an unseen domain leads to significant performance drop. To address such an issue, this paper proposes a novel coarseto-fine feature adaptation approach to cross-domain object detection. At the coarse-grained stage, different from the rough image-level or instance-level feature alignment used in the literature, foreground regions are extracted by adopting the attention mechanism, and aligned according to their marginal distributions via multi-layer adversarial learning in the common feature space. At the fine-grained stage, we conduct conditional distribution alignment of foregrounds by minimizing the distance of global prototypes with the same category but from different domains. Thanks to this coarse-to-fine feature adaptation, domain knowledge in foreground regions can be effectively transferred. Extensive experiments are carried out in various cross-domain detection scenarios. The results are state-of-the-art, which demonstrate the broad applicability and effectiveness of the proposed approach. Copyright © 2020, The Authors. All rights reserved.

关键词： Object recognition

Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Dou, Yingtong Liu, Zhiwei Sun, Li Deng, Yutong Peng, Hao Yu, Philip S. Department of Computer Science University of Illinois at Chicago United States School of Computer Science Beijing University of Posts and Telecommunications China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University China

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, i.e., 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 open-source toolbox1. The CARE-GNN code and datasets are available at https://***/YingtongDou/CARE-GNN. Copyright © 2020, The Authors. All rights reserved.

关键词： Graph neural networks

High temperature performance of coaxial h-BN/CNT wires above 1,000 ℃:Thermionic electron emission and thermally activated conductivity

学校读者我要写书评

暂无评论

Nano Research 2019年第8期12卷 1855-1861页

作者： Xinhe Yang Peng Liu Duanliang Zhou Feng Gao Xinhe Wang Shiwei Lv Zi Yuan Xiang Jin Wei Zhao Haoming Wei Lina Zhang Jiandong Gao Qunqing Li Shoushan Fan Kaili Jiang State Key Laboratory of Low-Dimensional Quantum Physics Department of Physics and Tsinghua-Foxconn Nanotechnology Research CenterTsinghua UniversityBeijing 100084China Yantai HeFuXiang Ceramics Co. LtdYantai 265205China Fert Beijing Research Institute School of Microelectronics and Beijing Advanced Innovation Center for Big Data and Brain Computing (BDBC)Beihang UniversityBeijing 100191China

The development of wires and cables that can tolerate extremely high temperatures will be very important for probing extreme environments, such as in solar exploration, fire disasters, high-temperature materials processing, aeronautics and astronautics. In this paper, a lightweight high-temperature coaxial h-boron nitride (BN)/carbon nanotube (CNT) wire is synthesized by the chemical vapor deposition (CVD) epitaxial growth of h-BN on CNT yarn. The epitaxially grown h-BN acts as both an insulating material and a jacket that protects against oxidation. It has been shown that the thermionic electron emission (1,200 K) and thermally activated conductivity (1,000 K) are two principal mechanisms for insulation failure of h-BN at high temperatures. The thermionic emission of h-BN can provide the work function of h-BN, which ranges from 4.22 to 4.61 eV in the temperature range of 1,306-1,787 K. The change in the resistivity of h-BN with temperature follows the ohmic conduction model of an insulator, and it can provide the “electron activation energy”(the energy from the Fermi level to the conduction band of h-BN), which ranges from 2.79 to 3.08 eV, corresponding to a band gap for h-BN ranging from 5.6 to 6.2 eV. However, since the leakage current is very small, both phenomena have no obvious influence on the signal transmission at the working temperature. This lightweight coaxial h-BN/CNT wire can tolerate 1,200 ℃ in air and can transmit electrical signals as normal. It is hoped that this lightweight high-temperature wire will open up new possibilities for a wide range of applications in extreme high-temperature conditions.

关键词： high temperature wire carbon nanotube (CNT) h-boron nitride (h-BN) work function bandgap

Gait-Based Age Estimation with Deep Convolutional Neural Network

学校读者我要写书评

暂无评论

Gait-Based Age Estimation with Deep Convolutional Neural Net...

IAPR International Conference on Biometrics (ICB)

作者： Shaoxiong Zhang Yunhong Wang Annan Li Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China

Gait is a unique biometric identifier for its non-invasive and low-cooperative features. Gait-based attribute recognition can play a crucial role in a wide range of applications, such as intelligent surveillance and criminal retrieval. However, due to the lack of data, there are relatively few studies which apply deep convolutional neural networks on gait attribute recognition. In this study, with the new progress in public gait dataset, we proposed a deep convolutional neural network with multi-task learning for gait-based human age estimation. Gait energy images are directly fed into our model for age estimation while gender information is also integrated for improving the performance of age estimation. The experiments on large-scale OULP-Age dataset show that our model outperforms the state-of-the-art.

关键词：

HCNet: An SDN Enabled Virtual Network Management System for Hybrid Clouds

学校读者我要写书评

暂无评论

HCNet: An SDN Enabled Virtual Network Management System for ...

IEEE Symposium on Computers and Communications (ISCC)

作者： Jie Sun Nan Zhang Tianyu Wo Xudong Liu Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China

Hybrid clouds require scalable, high performance virtual networks (VN) to facilitate the resource interoperability among multiple clouds. However, current VNs in hybrid clouds face the following challenges: (1) Management complexity. The VNs in hybrid clouds need to support inter-cloud resource deployment with multi-tenancy and full address space virtualization, and therefore are complex to manage. Meanwhile, the VNs are vulnerable to failures due to their large scale. (2) Performance limitation. Hybrid clouds rely on the Internet to support inter-cloud data transmission. Therefore without a meticulous design, the inter-cloud VNs would suffer from a performance limitation introduced by the Internet, e.g., the intercloud bandwidth provided by the Internet is much lower and more fluctuant than that of the intra-cloud networks. To the best of our knowledge, most existing VN solutions cannot solve both of these challenges *** this paper we introduce HCNet, a hybrid cloud virtual network management system. HCNet makes use of Software Defined Networking (SDN) and: (1) supports multi-tenancy and full address space virtualization on both Layer-2 and Layer-3 networks through the help of its elaborated packet processing pipeline, (2) leverages a dynamic load balance policy atop multiple inter-cloud gateways to achieve better performance on inter-cloud virtual networking, (3) maintains master-slave backup relationship based on paxos protocol to deal with controller outages. The experiment results indicate that HCNet achieves significant inter-cloud communication performance gain with respect to packet loss. Moreover, in presence of controller failures, HCNet is able to recover in about 5 seconds.

关键词： Cloud computing Logic gates Pipelines Bandwidth Network topology data communication Virtualization