检索结果-内蒙古大学图书馆

Graph structure learning with Variational Information Bottleneck

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Sun, Qingyun Li, Jianxin Peng, Hao Wu, Jia Fu, Xingcheng Ji, Cheng Yu, Philip S. Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China School of Computer Science and Engineering Beihang University Beijing100191 China Shenyuan Honors College Beihang University Beijing100191 China School of Computing Macquarie University Sydney Australia Department of Computer Science University of Illinois at Chicago Chicago United States

Graph Neural Networks (GNNs) have shown promising results on a broad spectrum of applications. Most empirical studies of GNNs directly take the observed graph as input, assuming the observed structure perfectly depicts the accurate and complete relations between nodes. However, graphs in the real-world are inevitably noisy or incomplete, which could even exacerbate the quality of graph representations. In this work, we propose a novel Variational Information Bottleneck guided Graph Structure Learning framework, namely VIB-GSL, in the perspective of information theory. VIB-GSL advances the Information Bottleneck (IB) principle for graph structure learning, providing a more elegant and universal framework for mining underlying task-relevant relations. VIB-GSL learns an informative and compressive graph structure to distill the actionable information for specific downstream tasks. VIB-GSL deduces a variational approximation for irregular graph data to form a tractable IB objective function, which facilitates training stability. Extensive experimental results demonstrate that the superior effectiveness and robustness of VIB-GSL. Copyright © 2021, The Authors. All rights reserved.

关键词： Graph neural networks

TOPOSCH: Latency-Aware Scheduling Based on Critical Path Analysis on Shared YARN Clusters

学校读者我要写书评

暂无评论

TOPOSCH: Latency-Aware Scheduling Based on Critical Path Ana...

IEEE International Conference on Cloud computing, CLOUD

作者： Chunming Hu Jianyong Zhu Renyu Yang Hao Peng Tianyu Wo Shiqing Xue Xiaoqiang Yu Jie Xu Rajiv Ranjan Beijing Advanced Innovation Center for Big Data and Brain Computing (BDBC) Beihang University China School of Computing University of Leeds UK School of Cyber Science and Technology Beihang University China School of Computing Newcastle University UK

ISBN: (数字)9781728187808

ISBN: (纸本)9781728187815

Balancing resource utilization and application QoS is a long-standing research topic in cluster resource management. big data YARN clusters need to co-schedule diverse workloads on shared resources including batch processing jobs, streaming jobs, and other long-running applications such as web services, database services, etc. Current resource managers are only responsible for resource allocation among applications/jobs but completely unaware of runtime QoS requirements of interactive and latency-sensitive applications. Prior works to maximize the QoS of monolithic applications ignore inherent dependencies and temporal-spatio performance variability of components, characteristics of distributed applications primarily driven by microservices. In this paper, we present Toposch, a new resource management system to adaptively co-locate batch tasks and microservices by harvesting runtime latency. In particular, Toposch tracks full footprints of every request across microservices over time. A latency graph is periodically generated for identifying victim microservices through an end-to-end latency critical path analysis. We then exploit per-microservice and per-node risk assessment to gauge the visible resources to the capacity scheduler in YARN. Execution of batch tasks are adaptively throttled or delayed, thereby avoiding latency increase due to node over-saturation. TOPOSCH is integrated with YARN and experiments show that the latency of DLRAs can be reduced by up to 39.8% against the default capacity scheduling in YARN.

关键词： Cloud computing Runtime Processor scheduling Quality of service Resource management Yarn Task analysis

Strong coupling of antiferromagnetic resonance with sub-THz cavity fields

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Bialek, Marcin Zhang, J. Yu, H. Ansermet, J.-Ph. Lausanne1015 Switzerland Fert Beijing Institute School of Microelectronics Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China

Strong coupling of electromagnetic cavity fields with antiferromagnetic spin waves in hematite (α-Fe2O3) was achieved above room temperature. A cube of hematite was placed in a metallic tube and transmission was measured, using a continuous-wave THz spectrometer. Spectra, collected as a function of temperature, reveal the formation of magnetic polaritons. © 2020, CC BY-SA.

关键词： Hematite

Convolutional Neural Network Pruning: A Survey

学校读者我要写书评

暂无评论

Convolutional Neural Network Pruning: A Survey

第三十九届中国控制会议

作者： Sheng Xu Anran Huang Lei Chen Baochang Zhang School of Automatic Science and Eletrical Engineering Beihang University State Key Laboratory of Software Development Environment Beijing Advanced Innovation Center for Big Data and Brain Computing

Deep convolutional neural networks have enabled remarkable progress over the last years on a variety of visual tasks,such as image recognition, speech recognition, and machine translation. These tasks contribute many to machine ***, developments of deep convolutional neural networks to a machine terminal remains challenging due to massive number of parameters and float operations that a typical model contains. Therefore, there is growing interest in convolutional neural network pruning. Existing work in this field of research can be categorized according to three dimensions: pruning method,training strategy, estimation criterion.

关键词： convolutional neural networks machine intelligence pruning method training strategy estimation criterion

Weak ties strengthen anger contagion in social media

学校读者我要写书评

暂无评论

arXiv 2020年

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

Increasing evidence suggests that, similar to face-to-face communications, human emotions also spread in online social media. However, the mechanisms underlying this emotion contagion, for example, whether different feelings spread in unlikely ways or how the spread of emotions relates to the social network, is rarely investigated. Indeed, because of high costs and spatio-temporal limitations, explorations of this topic are challenging using conventional questionnaires or controlled experiments. Because they are collection points for natural affective responses of massive individuals, online social media sites offer an ideal proxy for tackling this issue from the perspective of computational social science. In this paper, based on the analysis of millions of tweets in Weibo, surprisingly, we find that anger travels easily along weaker ties than joy, meaning that it can infiltrate different communities and break free of local traps because strangers share such content more often. Through a simple diffusion model, we reveal that weaker ties speed up anger by applying both propagation velocity and coverage metrics. To the best of our knowledge, this is the first time that quantitative long-term evidence has been presented that reveals a difference in the mechanism by which joy and anger are disseminated. With the extensive proliferation of weak ties in booming social media, our results imply that the contagion of anger could be profoundly strengthened to globalize its negative impact. Copyright © 2020, The Authors. All rights reserved.

关键词： Social networking (online)

An Improved Deep Learning Approach for Thyroid Nodule Diagnosis

学校读者我要写书评

暂无评论

An Improved Deep Learning Approach for Thyroid Nodule Diagno...

IEEE International Symposium on Biomedical Imaging

作者： Xiangdong Guo Haifeng Zhao Zhenyu Tang School of Computer Science and Technology Anhui University Hefei Anhui China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China

ISBN: (数字)9781538693308

ISBN: (纸本)9781538693315

Although thyroid ultrasonography (US) has been widely applied, it is still difficult to distinguish benign and malignant nodules. Currently, convolutional neural network (CNN) based methods have been proposed and shown promising performance for benign and malignant nodules classification. It is known that the US images are usually captured in multi-angles, and the same thyroid in different US images have inconsistent content. However, most of the existing CNN based methods extract features using fixed convolution kernels, which could be a big issue for processing US images. Moreover, fully-connected (FC) layers are usually adopted in CNN, which could cause the loss of inter-pixel relations. In this paper, we propose a new CNN which is integrated with squeeze-and-excitation (SE) module and maximum retention of inter-pixel relations module (CNN-SE-MPR). It can adaptively select features from different US images and preserve the inter-pixel relations. Moreover, we introduce transfer learning to avoid problems such as local optimum and data insufficiency. The proposed network is tested on 407 thyroid US images collected from cooperated hospitals. Confirmed by ablation experiments and the comparison experiments under the state-of-the-art methods, it is shown that our method improves the accuracy of the diagnosis results.

关键词： Feature extraction Cancer Convolution Training Sensitivity Machine learning Ultrasonography

Foreword to the Special Issue

学校读者我要写书评

暂无评论

Journal of Systems Science & Complexity 2019年第1期32卷 1-2页

作者： GAO Xiao-Shan LI Hongbo WANG Dongming Key Laboratory of Mathematics Mechanization Academy of Mathematics and Systems Science University of Chinese Academy of Sciences Chinese Academy of Sciences LMIB–SKLSDE–School of Mathematics and Systems Science/Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Centre National de la Recherche Scientifique

On May 12,2019 we shall celebrate the centenary birthday of the late Professor Wu Wen-Tsun (1919-2017),one of the most famous and influential mathematicians in *** made foundational contributions to the field of topology and established Mathematics Mechanization as a *** devoted himself to an academic career of more than six decades with leadership and extensive activities of research and education across mathematics to computer science and artificial *** scope of his research spans from algebraic topology, differential topology,and algebraic geometry to automated reasoning,symbolic computation, and game theory,and to the history of *** early work in topology was a major breakthrough,leading to well-known and now classical results including the characteristic class and formulas named after *** the late 1970s,he pioneered the research of Mathematics Mechanization through his invention of the "Wu method",which revolutionized the field of automated reasoning.

关键词： shall celebrate centenary birthday established Mathematics

System architecture for high-performance permissioned blockchains

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2019年第6期13卷 1151-1165页

作者： Libo FENG Hui ZHANG Wei-Tek TSAI Simeng SUN State Key Laboratory of Software Development Environment Beihang UniversityBeijing 100191China Digital Society&Blockchain Laboratory School of Computer ScienceBeihang UniversityBeijing 100191China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang UniversityBeijing 100191China School of Computing Informatics and Decision Systems EngineeringArizona State UniversityTempeUSA

Blockchain(BC),as an emerging distributed database technology with advanced security and reliability,has attracted much attention from experts who devoted to efinance,intellectual property protection,the internet of things(IoT)and so ***,the inefficient transaction processing speed,which hinders the BC’s widespread,has not been well tackled *** this paper,we propose a novel architecture,called Dual-Channel Parallel Broadcast model(DCPB),which could address such a problem to a greater extent by using three methods which are dual communication channels,parallel pipeline processing and block broadcast *** the dual-channel model,one channel processes transactions,and the other engages in the execution of *** parallel pipeline processing allows the system to operate *** block generation strategy improves the efficiency and speed of *** experiments have been applied to BeihangChain,a simplified prototype for BC system,illustrates that its transaction processing speed could be improved to 16K transaction per second which could well support many real-world scenarios such as BC-based energy trading system and Micro-film copyright trading system in CCTV.

关键词： blockchain concurrency performance dualchannel model parallel pipeline consensus algorithm

SUGAR: Subgraph neural network with reinforcement pooling and self-supervised mutual information mechanism

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Sun, Qingyun Li, Jianxin Peng, Hao Wu, Jia Ning, Yuanxing Yu, Phillip S. He, Lifang Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China School of Computer Science and Engineering Beihang University Beijing100191 China Department of Computing Macquarie University Sydney Australia Department of Computer Science University of Illinois at Chicago Chicago United States Department of Computer Science and Engineering Lehigh University BethlehemPA United States

Graph representation learning has attracted increasing research attention. However, most existing studies fuse all structural features and node attributes to provide an overarching view of graphs, neglecting finer substructures' semantics, and suffering from interpretation enigmas. This paper presents a novel hierarchical subgraph-level selection and embedding-based graph neural network for graph classification, namely SUGAR, to learn more discriminative subgraph representations and respond in an explanatory way. SUGAR reconstructs a sketched graph by extracting striking subgraphs as the representative part of the original graph to reveal subgraph-level patterns. To adaptively select striking subgraphs without prior knowledge, we develop a reinforcement pooling mechanism, which improves the generalization ability of the model. To differentiate subgraph representations among graphs, we present a self-supervised mutual information mechanism to encourage subgraph embedding to be mindful of the global graph structural properties by maximizing their mutual information. Extensive experiments on six typical bioinformatics datasets demonstrate a significant and consistent improvement in model quality with competitive performance and interpretability. Copyright © 2021, The Authors. All rights reserved.

关键词： Reinforcement learning