检索结果-内蒙古大学图书馆

A general scalable and elastic matching service for content-based publish/subscribe systems

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE 2015年第1期27卷 94-118页

作者： Ma, Xingkong Wang, Yijie Pei, Xiaoqiang Li, Xiaoyong Natl Univ Def Technol Coll Comp Sci & Technol Parallel & Distributed Proc Lab Changsha 410073 Hunan Peoples R China

Characterized by the emergence of a large number of live content, the emergency applications have received increasing attention in recent years. Providing a general and scalable event, matching service can precisely notify users latest information that they are interested in. However, because the live content arrival rate may churn significantly in a short time and subscriptions with various patterns tend to be skewed, it is challenging to increase the generality, scalability, and elasticity of the matching process. We propose a novel parallel event matching service based on the cloud computing environment, called GSEM, to satisfy these requirements. GSEM first presents a two-hop framework and a general subscription pattern to handle various patterns of subscriptions. To provide scalable matching service, a hybrid content space partition scheme is proposed to divide large skewed subscriptions into multiple small clusters managed by a group of parallel servers. To adapt to the sudden change of event arrival rate, GSEM elastically adjusts the scale of servers and rebalances their workloads through a performance-aware detection technique. A prototype deployment on the OpenStack platform shows that GSEM achieves scalable matching throughput with the growth of servers, elastic service capacity with the change of event arrival rate, and significantly outperforms the existing cloud based systems in various workloads. Copyright (C) 2014 John Wiley & Sons, Ltd.

关键词： event matching content-based publish/subscribe content space partitioning cloud computing emergency application

来源：评论

学校读者我要写书评

暂无评论

SCGraph: Accelerating Sample-based GNN Training by Staged Caching of Features on GPUs 20

SCGraph: Accelerating Sample-based GNN Training by Staged Ca...

引用

20th IEEE Int Symposium on parallel and distributed processing with Applicat / 15th IEEE Int Conf on Social Comp and Networking / 12th IEEE Int Conf on Big Data and Cloud Comp / 12th IEEE Int Conf on Sustainable Comp and Commun

作者： He, Yuqi Lai, Zhiquan Ran, Zhejiang Zhang, Lizhi Li, Dongsheng Natl Univ Def Technol Coll Comp Natl Key Lab Parallel & Distributed Proc Changsha Peoples R China

ISBN: (纸本)9781665464970

Graph neural networks (GNNs) have been becoming important tools for processing structured graph data and successfully applied to multiple graph-based application scenarios. The existing GNN systems adopt sample-based training on large-scale graphs over multiple GPUs. Although they support large-scale graph training, large data loading overhead of transferring vertex features between CPUs and GPUs is still a bottleneck. In this work, we propose SCGraph, a method that supports GPU high-speed feature caching. SCGraph classifies the graph vertices sorted by out-degrees. For high out-degree vertices, SCGraph sets grading caches via different GPUs to increase the overall cache content through NVLink high-speed data transmission between them. For low out-degree vertices, SCGraph expands training vertices' neighborhood in advance to regenerate cache. We evaluate SCGraph against two state-of-the-art industrial GNN frameworks, i.e., DGL and PaGraph on various benchmarks. Experimental results show that SCGraph improves the cache hit rate over GPUs up to 23.6%, and achieves up to 1.71x performance speedup over the state-of-the-art baselines while the convergence almost constant.

关键词： graph neural networks feature caching sampling

来源：评论

学校读者我要写书评

暂无评论

A Scalable and Reliable Matching Service for Content-Based Publish/Subscribe Systems

引用

IEEE TRANSACTIONS ON CLOUD COMPUTING 2015年第1期3卷 1-13页

作者： Ma, Xingkong Wang, Yijie Pei, Xiaoqiang Natl Univ Def Technol Sci & Technol Parallel & Distributed Proc Lab Coll Comp Changsha 410073 Hunan Peoples R China

Characterized by the increasing arrival rate of live content, the emergency applications pose a great challenge: how to disseminate large-scale live content to interested users in a scalable and reliable manner. The publish/subscribe (pub/sub) model is widely used for data dissemination because of its capacity of seamlessly expanding the system to massive size. However, most event matching services of existing pub/sub systems either lead to low matching throughput when matching a large number of skewed subscriptions, or interrupt dissemination when a large number of servers fail. The cloud computing provides great opportunities for the requirements of complex computing and reliable communication. In this paper, we propose SREM, a scalable and reliable event matching service for content-based pub/sub systems in cloud computing environment. To achieve low routing latency and reliable links among servers, we propose a distributed overlay SkipCloud to organize servers of SREM. Through a hybrid space partitioning technique HPartition, large-scale skewed subscriptions are mapped into multiple subspaces, which ensures high matching throughput and provides multiple candidate servers for each event. Moreover, a series of dynamics maintenance mechanisms are extensively studied. To evaluate the performance of SREM, 64 servers are deployed and millions of live content items are tested in a CloudStack testbed. Under various parameter settings, the experimental results demonstrate that the traffic overhead of routing events in SkipCloud is at least 60 percent smaller than in Chord overlay, the matching rate in SREM is at least 3.7 times and at most 40.4 times larger than the single-dimensional partitioning technique of BlueDove. Besides, SREM enables the event loss rate to drop back to 0 in tens of seconds even if a large number of servers fail simultaneously.

关键词： Publish/subscribe event matching overlay construction content space partitioning cloud computing

来源：评论

学校读者我要写书评

暂无评论

A General Scalable and Elastic Content-Based Publish/Subscribe Service

引用

IEEE TRANSACTIONS ON parallel AND distributed SYSTEMS 2015年第8期26卷 2100-2113页

作者： Wang, Yijie Ma, Xingkong Natl Univ Def Technol Sci & Technol Parallel & Distributed Proc Lab Coll Comp Changsha 410073 Hunan Peoples R China

The big data era is characterized by the emergence of live content with increasing complexities of data dimensionality and data sizes, which poses a new challenge to emergency applications: how to timely disseminate large-scale live content to users who are interested in. The publish/subscribe (pub/sub) model is widely used to disseminate data because of its possibility of expanding the system to Internet-scale size. However, existing pub/sub systems are inadequate to meet the requirement of disseminating live content in the big data era, since their multi-hop routing techniques and coarse-grained partitioning techniques lead to a low matching throughput, and their upload capacities do not scale well. In this paper, we propose a general scalable and elastic pub/sub service based on the cloud computing environment, called GSEC. For generality, we propose a two-layer pub/sub framework to support the dissemination with diverse data sizes and data dimensionality. For scalability, a hybrid space partitioning technique is proposed to achieve high matching throughput, which divides subscriptions into multiple clusters in a hierarchical manner. Moreover, a helper-based content distribution technique is proposed to achieve high upload bandwidth, where servers act as both providers and coordinators to fully explore the upload capacity of the system. For elasticity, we propose a performance-aware provisioning technique to adjust the scale of servers to adapt to the churn workloads. To evaluate the performance of GSEC, about 1,000 servers are deployed and hundreds of thousands of live content items are tested in our CloudStack-based testbed. Extensive experiments confirm that GSEC can linearly increase the capacities of event matching and content distribution with the growth of servers, adaptively adjust these capacities in tens of seconds according to the churn workloads, and significantly outperforms the state-of-the-art approaches under various parameter settings.

关键词： Publish/subscribe event matching space partitioning content distribution cloud computing

来源：评论

学校读者我要写书评

暂无评论

Enabling Imagination: Generative Adversarial Network-Based Object Finding in Robotic Tasks 24th

Enabling Imagination: Generative Adversarial Network-Based O...

引用

24th International Conference on Neural Information processing (ICONIP)

作者： Che, Huimin Hu, Ben Ding, Bo Wang, Huaimin Natl Univ Def Technol Natl Key Lab Parallel & Distributed Proc Coll Comp Changsha Peoples R China

ISBN: (纸本)9783319701363;9783319701356

The skill to find objects in a real world situation is important for mobile robots. Existing works of robotic vision-based object finding is based on the traditional training and classification paradigm, which means that a robot can only detect objects with the fixed and pre-trained classification labels. It is of great challenge for robots to find an untrained object, even if a complex description of the object has been given. In this paper, we proposed a vision-based object detection approach for robotic finding names Generative Search. It is inspired by the object detection model that when an unfamiliar object needs to be found through a complex description, human would "imagine" the object in his or her brain and then find the object which is mostly like the imagined object profile. By adopting a Generative Adversarial Network (GAN), our approach enables the robot to generate the object virtually according to the given description. Then, we use pre-trained deep neural networks to match the generated image with images in the robotic vision. At the implementation level, we adopt the cloud robotic architecture to promote the algorithm efficiency. The experiments on both open datasets and real robotic scenarios have proved the significant promotion of object finding accuracy when a robot searching an unfamiliar object with a complex description.

关键词： Robotic object finding GAN Image matching

来源：评论

学校读者我要写书评

暂无评论

Multiple Kernel Clustering Framework with Improved Kernels 26

Multiple Kernel Clustering Framework with Improved Kernels

引用

26th International Joint Conference on Artificial Intelligence (IJCAI)

作者： Wang, Yueqing Liu, Xinwang Dou, Yong Li, Rongchun NUDT Natl Lab Parallel & Distributed Proc Changsha 410073 Peoples R China

ISBN: (纸本)9780999241103

Multiple kernel clustering (MKC) algorithms have been successfully applied into various applications. However, these successes are largely dependent on the quality of pre-defined base kernels, which cannot be guaranteed in practical applications. This may adversely affect the clustering performance. To address this issue, we propose a simple while effective framework to adaptively improve the quality of base kernels. Under our framework, we instantiate three MKC algorithms based on the widely used multiple kernel k-means clustering (MKKM), MKKM with matrix-induced regularization (MKKM-MR) and co-regularized multi-view spectral clustering (CRSC). After that, we design the corresponding algorithms with proved convergence to solve the resultant optimization problems. To the best of our knowledge, our framework fills the gap between kernel adaption and clustering procedure for the first time in the literature and is readily extendable. Extensive experimental research has been conducted on 7 MKC benchmarks. As is shown, our algorithms consistently and significantly improve the performance of the base MKC algorithms, indicating the effectiveness of the proposed framework. Meanwhile, our framework shows better performance than compared ones with imperfect kernels.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Scalable and elastic total order in content-based publish/subscribe systems

引用

COMPUTER NETWORKS 2015年第Jun.4期83卷 297-314页

作者： Ma, Xingkong Wang, Yijie Pei, Xiaoqiang Xu, Fangliang Natl Univ Def Technol Sci & Technol Parallel & Distributed Proc Lab Coll Comp Changsha 410073 Hunan Peoples R China

Total order as a messaging guarantee scheme ensures that events sent to a set of subscribers are delivered by these subscribers in the same order. It has become increasingly important in content-based publish/subscribe (pub/sub) systems. Due to the large-scale live content and the churn workloads in the big data era, current emergency applications present a new challenge: how to provide a scalable and elastic total order service in content-based pub/sub systems. Most existing total order approaches cannot adapt to the churn workloads, and generate high delivery latency in the face of high arrival rate of live content. To this end, we propose a scalable and elastic total order service, called SETO, for content-based pub/sub systems in the cloud computing environment. SETO uses a two-layer pub/sub framework to decouple the event matching service and the total order service. In this framework, events are forwarded to their interested subscribers by multiple parallel servers. Through a preceding graph building technique, non-conflicting events in the same server are allowed to be delivered simultaneously, which greatly reduces the delivery latency. The performance-aware provisioning technique in SETO elastically adjusts the scale of servers to adapt to the churn workloads. To evaluate the performance of SETO, tens of servers and thousands of subscribers are deployed in our CloudStack testbed. Extensive experiments confirm that SETO can linearly reduce the delivery latency with the growth of servers, adaptively adjust the scale of servers in less than 5 s, and significantly outperforms the state-of-the-art approaches under diverse parameter settings. (C) 2015 Elsevier B.V. All rights reserved.

关键词： Total order Publish/subscribe Content-based Data dissemination Cloud computing

来源：评论

学校读者我要写书评

暂无评论

Poster Abstract: Model Average-based distributed Training for Sparse Deep Neural Networks

Poster Abstract: Model Average-based Distributed Training fo...

引用

39th IEEE International Conference on Computer Communications (IEEE INFOCOM)

作者： Yang, Yuetong Lai, Zhiquan Cai, Lei Li, Dongsheng Natl Univ Def Technol Sch Comp Natl Key Lab Parallel & Distributed Proc Changsha Peoples R China

ISBN: (数字)9781728186955

ISBN: (纸本)9781728186955

distributed training of large-scale deep neural networks(DNNs) is a challenging work for it's time costing and complicated communication. Existing works have achieved scalable performance on GPU clusters for dense DNNs in the computer vision area. However, little progress has been made on the distributed training of sparse DNNs which is commonly used in the area of natural language processing (NLP). In this poster, we introduce SA-HMA, a sparsity -aware hybrid training method for sparse deep models. SA-HMA combines Model Average (MA) and synchronous optimization methods together, expecting to reduce the communication cost for spare model training. The experimental results show that SA-HMA achieves 133x speedup over the state-of-the-art work.

关键词： Training Natural language processing Convergence Throughput Computational modeling Neural networks Machine learning

来源：评论

学校读者我要写书评

暂无评论

Cloudroid: A Cloud Framework for Transparent and QoS-aware Robotic Computation Outsourcing 10

Cloudroid: A Cloud Framework for Transparent and QoS-aware R...

引用

10th IEEE International Conference on Cloud Computing (CLOUD)

作者： Hu, Ben Wang, Huaimin Zhang, Pengfei Ding, Bo Che, Huimin Natl Univ Def Technol Natl Key Lab Parallel & Distributed Proc Changsha 410073 Hunan Peoples R China

ISBN: (纸本)9781538619933

Many robotic tasks require heavy computation, which can easily exceed the robot's onboard computer capability. A promising solution to address this challenge is outsourcing the computation to the cloud. However, exploiting the potential of cloud resources in robotic software is difficult, because it involves complex code modification and extensive (re) configuration procedures. Moreover, quality of service (QoS) such as timeliness, which is critical to robot's behavior, have to be considered. In this paper, we propose a transparent and QoS-aware software framework called Cloudroid for cloud robotic applications. This framework supports direct deployment of existing robotic software packages to the cloud, transparently transforming them into Internet-accessible cloud services. And with the automatically generated service stubs, robotic applications can outsource their computation to the cloud without any code modification. Furthermore, the robot and the cloud can cooperate to maintain the specific QoS property such as request response time, even in a highly dynamic and resource-competitive environment. We evaluated Cloudroid based on a group of typical robotic scenarios and a set of software packages widely adopted in real-world robot practices. Results show that robots capability can be enhanced significantly without code modification and specific QoS objectives can be guaranteed. In certain tasks, the "cloud + robot" setup shows improved performance in orders of magnitude compared with the robot native setup.

关键词： Cloud robotics Platform as a service Computation outsourcing Quality of service

来源：评论

学校读者我要写书评

暂无评论

A subspace ensemble framework for classification with high dimensional missing data

引用

MULTIDIMENSIONAL SYSTEMS AND SIGNAL procESSING 2017年第4期28卷 1309-1324页

作者： Gao, Hang Jian, Songlei Peng, Yuxing Liu, Xinwang Natl Univ Def Technol Coll Comp Sci & Technol Parallel & Distributed Proc Lab Changsha 410073 Hunan Peoples R China

Real world classification tasks may involve high dimensional missing data. The traditional approach to handling the missing data is to impute the data first, and then apply the traditional classification algorithms on the imputed data. This method first assumes that there exist a distribution or feature relations among the data, and then estimates missing items with existing observed values. A reasonable assumption is a necessary guarantee for accurate imputation. The distribution or feature relations of data, however, is often complex or even impossible to be captured in high dimensional data sets, leading to inaccurate imputation. In this paper, we propose a complete-case projection subspace ensemble framework, where two alternative partition strategies, namely bootstrap subspace partition and missing pattern-sensitive subspace partition, are developed for incomplete datasets with even missing patterns and uneven missing patterns, respectively. Multiple component classifiers are then separately trained in these subspaces. After that, a final ensemble classifier is constructed by a weighted majority vote of component classifiers. In the experiments, we demonstrate the effectiveness of the proposed framework over eight high dimensional UCI datasets. Meanwhile, we apply the two proposed partition strategies over data sets with different missing patterns. As indicated, the proposed algorithm significantly outperforms existing imputation methods in most cases.

关键词： High dimensional data Missing data Subspace ensemble Extreme learning machine

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：