检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks

作者： Hao Yu Zhaoning Zhang Zijie Zhu Wang Xiong Gen Zhang Science and Technology on Parallel and Distributed Laboratory National University of Defense Technology Changsha China College of Meteorology and Oceanology National University of Defense Technology Changsha China College of Computer National University of Defense Technology Changsha China

Similarity of nominal data plays fundamental roles in numerous fields of both machine learning and data mining. Unlike the similarity of numerical data, that of nominal data is much more difficult to describe, and few efforts have been done for it. Although existing nominal similarity measures can reveal a part of data properties, they suffer from low accuracy due to ignoring value relationships or integrating multi-view relationships inappropriately. In this paper, we propose a novel hierarchical measure for nominal data similarity (HNS). The HNS leverages the intrinsic data characteristics by considering low-level information both within and between attributes, and hierarchically seizes the value distributions, attribute interactions and attribute to object contributions. Meanwhile, it aggregates multi-view relationships trough a bottom to top framework, remaining consistency as well as complementary details. We theoretically analyzed this measure, and experiments on six UCI data sets demonstrate that the HNS outperforms the state-of-the-art nominal similarity measures in term of target alignment and clustering accuracy.

关键词： Sea measurements Frequency measurement Task analysis Medical services distributed databases Machine learning

来源：评论

学校读者我要写书评

暂无评论

Optimistic data consistency maintenance method based on key-attributes

引用

Ruan Jian Xue Bao/Journal of Software 2008年第8期19卷 2114-2126页

作者： Zhou, Jing Wang, Yi-Jie Li, Si-Kun National Key Laboratory for Parallel and Distributed Processing School of Computer National University of Defense Technology Changsha 410073 China

The features of simple description, small updates item and weak dependence are the main characteristics of updates of key-attributes in P2P systems. Accordingly, an optimistic data consistency maintenance method based on key-attributes is proposed. In the method, the update of key-attributes is separated from user update requests. Key-Updates are propagated by latency-overlay update propagation model, that is, updates are always propagated to the nodes having maximum or minimum latency, and assured and uncertain propagation paths of updates are all taken into account. Based on classifying key-update conflicts, a double-level reconciling mechanism including buffer preprocessing and update-log processing is applied to detect and reconcile conflicts, and then conflicts are solved by policies as last-writer-win and divide-and-rule. Lastly, update-log management method and maintenance method brought by node failure and network partitioning are discussed for the above is deployed based on the information storied in update-log. Delaying key-attributes updates cannot occur by the optimistic disposal method, and then it cannot depress efficiency of resource location based on key-attributes, which adapts well to P2P systems for Internet. The simulation results show that it is an effective optimistic data consistency maintenance method, achieving good consistency overhead, resource location and resource access overhead, and having strong robustness.

关键词： Maintenance

来源：评论

学校读者我要写书评

暂无评论

Benchmarking the task graph scheduling algorithms

Benchmarking the task graph scheduling algorithms

引用

International Symposium on parallel processing

作者： Y.-K. Kwok I. Ahmad Parallel Processing Laboratory School of Electrical and Computer Engineering Purdue University West Lafayette IN USA Department of Computer Science Hong Kong University of Science and Technology Hong Kong China

The problem of scheduling a weighted directed acyclic graph (DAG) to a set of homogeneous processors to minimize the completion time has been extensively studied. The NP-completeness of the problem has instigated researchers to propose a myriad of heuristic algorithms. While these algorithms are individually reported to be efficient, it is not clear how effective they are and how well they compare against each other. A comprehensive performance evaluation and comparison of these algorithms entails addressing a number of difficult issues. One of the issues is that a large number of scheduling algorithms are based upon radically different assumptions, making their comparison on a unified basis a rather intricate task. Another issue is that there is no standard set of benchmarks that can be used to evaluate and compare these algorithms. Furthermore, most algorithms are evaluated using small problem sizes, and it is not clear how their performance scales with the problem size. The authors first provide a taxonomy for classifying various algorithms into different categories according to their assumptions and functionalities. They then propose a set of benchmarks which are of diverse structures without being biased towards a particular scheduling technique and still allow variations in important parameters. They have evaluated 15 scheduling algorithms, and compared them using the proposed benchmarks. Based upon the design philosophies and principles behind these algorithms, they interpret the results and discuss why some algorithms perform better than the others.

关键词： Scheduling algorithm Processor scheduling parallel processing Concurrent computing Heuristic algorithms Laboratories Computer science Taxonomy Algorithm design and analysis Scalability

来源：评论

学校读者我要写书评

暂无评论

Analysis and evaluation method for linpack benchmark

引用

Dongbei Daxue Xuebao/Journal of Northeastern University 2014年 35卷 102-107页

作者： Du, Yun-Fei Yang, Can-Qun Wang, Feng Yi, Hui-Zhan School of Computer National University of Defense Technology Changsha410073 China Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology Changsha410073 China

The basic algorithm of HPL was introduced. Two optimization methods of communication, i.e., advanced-lookahead and dynamic broadcasting algorithm, were proposed. The performances of the two optimization methods were evaluated on the Tianhe-2 system, and compared with the performance of traditional HPL. The Linpack evaluating methods were discussed, the choice methods of the key parameters affecting the performance were given, and the effect of the high-speed interconnection network on Linpack performance was analyzed. The results showed that the higher the node performance, the greater the effect of the network bandwidth and latency on the performances of HPL. ©, 2014, Northeastern University. All right reserved.

关键词： Large scale systems

来源：评论

学校读者我要写书评

暂无评论

Symmetric Non-negative Matrix Factorization Based Link Partition Method for Overlapping Community Detection

Symmetric Non-negative Matrix Factorization Based Link Parti...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Xiang Zhang Naiyang Guan Wenju Zhang Xuhui Huang Shuyi Wu Zhigang Luo Science and Technology on Parallel and Distributed Processing Laboratory College of Computer National University of Defense Technology Hunan P.R. China Institute of Software College of Computer National University of Defense Technology Hunan P.R. China Department of Computer Science and Technology College of Computer National University of Defense Technology Hunan P.R. China

ISBN: (纸本)9781479986989

Partitioning links rather than nodes is effective in overlapping community detection (OCD) on complex networks. However, it consumes high CPU and memory overheads because the volume of links is huge especially when the network is rather complex. In this paper, we proposes a symmetric non-negative matrix factorization (SNMF) based link partition method called SNMF-Link to overcome this deficiency. In particular, SNMF-Link represents data in a lower-dimensional space spanned by the node-link incidence matrix. By solving a lighter SNMF problem, SNMF-Link learns the clustering indicators of each links. Since traditional multiplicative update rule (MUR) based optimization algorithm for SNMF suffers from slow convergence, we applied the augmented Lagrangian method (ALM) to efficiently optimize SNMF. Experimental results show that SNMF-Link is much more efficient than the representative clustering algorithms without reducing the OCD performance.

关键词： Symmetric matrices Convergence Optimization Partitioning algorithms Chlorine Complex networks Image edge detection

来源：评论

学校读者我要写书评

暂无评论

Asynchronous Bundle Method for Large-Scale Regularized Risk Minimization

Asynchronous Bundle Method for Large-Scale Regularized Risk ...

引用

International Joint Conference on Neural Networks

作者： Menglong Lu Dawei Feng Linbo Qiao Dawen Ding Dongsheng Li Science and Technology on Parallel and Distributed Laboratory National University of Defense Technology Changsha China College of Computer National University of Defense Technology Changsha China CMC AS2 South CSC Asiainfo Nanchang China

Bundle method for regularized risk minimization (BMRM) is a variant of Cutting Plane Method (CPM). It performs efficiently in solving a convex minimization problem, which is a core part in a plethora of machine learning applications. Nonetheless, while exposed to the challenge of large-scale learning, the synchronous parallel implementation of BMRM easily encounters the straggler problem due to the diversity among heterogeneous working nodes' capability and unevenness in the inherent data distribution. In this paper, we propose a novel asynchronous distributed BMRM implementation, which employs an asynchronous computing window to fully explore the fast nodes' computational capabilities while reserving the good convergence of the BMRM. Extensive experiments show that the asynchronous BMRM algorithm has significant improvement of performance over its synchronous counterpart, and owns the ability to solve large-scale problems efficiently.

关键词： Estimation Linear programming Machine learning Risk management Convergence Servers Minimization

来源：评论

学校读者我要写书评

暂无评论

Design of an Indoor Exploration and Multi-Objective Navigation System

Design of an Indoor Exploration and Multi-Objective Navigati...

引用

Chinese Control Conference (CCC)

作者： Guoxian Zheng Lei Zhang Huaxi Yulin Zhang Bo Ding State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang China MIS Universite de Picardie Jules Verne Amiens France National Laboratory for Parallel and Distributed Processing National University of Defense Technology Changsha China

In this paper, we propose an indoor robot autonomous navigation system. The robot firstly explores in an unknown environment, and then navigates autonomously by using the explored map. The robot is equipped a 2D laser scanner as the main sensor. The laser scanner is used for path planning and frontier-based exploration. A 2D global occupancy map is built for path planning, frontier-based exploration and multi-objective autonomous navigation. Laser scans are transmitted into Simultaneous Localization and Mapping (SLAM) process in the exploration phase. In indoor environment, the exploration efficiency is improved by merging a heuristic algorithm. By using multi-threading technology and a 3D perception approach proposed in this paper, the robot equipped with a low-cost RGBD sensor can detect all kinds of obstacles to achieve highly reliable navigation in complicated 3D environment. Meanwhile, we develop a multi-objective navigation application to make human-robot interaction more convenient and satisfy multi-task deployment. Our approaches are demonstrated by experimental results.

关键词： Navigation Three-dimensional displays Robot sensing systems Lasers Path planning Two dimensional displays

来源：评论

学校读者我要写书评

暂无评论

RuleRAG: Rule-Guided Retrieval-Augmented Generation with Language Models for Question Answering

arXiv

引用

arXiv 2024年

作者： Chen, Zhongwu Xu, Chengjin Wang, Dingmin Huang, Zhen Dou, Yong Jiang, Xuhui Guo, Jian National Key Laboratory of Parallel and Distributed Computing College of Computer Science and Technology National University of Defense Technology China IDEA Research International Digital Economy Academy Department of Computer Science University of Oxford United Kingdom

Retrieval-augmented generation (RAG) has shown promising potential in knowledge intensive question answering (QA). However, existing approaches only consider the query itself, neither specifying the retrieval preferences for the retrievers nor informing the generators of how to refer to the retrieved documents for the answers, which poses a significant challenge to the QA performance. To address these issues, we propose Rule-guided Retrieval-Augmented Generation with LMs, which explicitly introduces rules for in-context learning (RuleRAG-ICL) to guide retrievers to recall related documents in the directions of rules and uniformly guide generators to reason attributed by the same rules. The combination of queries and rules can be used as fine-tuning data to update retrievers and generators, achieving better rule-based instruction-following ability (RuleRAG-FT). Moreover, most existing RAG datasets were constructed without considering rules and Knowledge Graphs (KGs) are recognized as providing high-quality rules. Therefore, we construct five rule-aware RAG benchmarks for QA, RuleQA, based on KGs to stress the significance of retrieval and reasoning with rules. Experiments on RuleQA demonstrate RuleRAG-ICL improves the retrieval quality of +89.2% in Recall@10 and answer accuracy of +103.1% in Exact Match, and RuleRAG-FT yields more enhancement. In addition, experiments on four existing RAG datasets show RuleRAG is also effective by offering rules in RuleQA to them, further proving the generalization of rule guidance in RuleRAG. Code and RuleQA are at https://***/r/RuleRAG. Copyright © 2024, The Authors. All rights reserved.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

Collaborative deep learning across multiple data centers

arXiv

引用

arXiv 2018年

作者： Xu, Kele Mi, Haibo Feng, Dawei Wang, Huaimin Chen, Chuan Zheng, Zibin Lan, Xu National Key Laboratory of Parallel and Distributed Processing Changsha China College of Computer National University of Defense Technology Changsha China School of Data and Computer Science Sun Yat-Sen University Guangzhou China Queen Mary University of London London United Kingdom

Valuable training data is often owned by independent organizations and located in multiple data centers. Most deep learning approaches require to centralize the multi-datacenter data for performance purpose. In practice, however, it is often infeasible to transfer all data to a centralized data center due to not only bandwidth limitation but also the constraints of privacy regulations. Model averaging is a conventional choice for data parallelized training, but its ineffectiveness is claimed by previous studies as deep neural networks are often non-convex. In this paper, we argue that model averaging can be effective in the decentralized environment by using two strategies, namely, the cyclical learning rate and the increased number of epochs for local model training. With the two strategies, we show that model averaging can provide competitive performance in the decentralized mode compared to the data-centralized one. In a practical environment with multiple data centers, we conduct extensive experiments using state-of-the-art deep network architectures on different types of data. Results demonstrate the effectiveness and robustness of the proposed method. Copyright © 2018, The Authors. All rights reserved.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Optimal and near-optimal allocation of precedence-constrained tasks to parallel processors: defying the high complexity using effective search techniques

Optimal and near-optimal allocation of precedence-constraine...

引用

International Conference on parallel processing (ICPP)

作者： I. Ahmad Yu-Kwong Kwok Department of Computer Science Hong Kong University of Science and Technology Hong Kong China Parallel Processing Laboratory School of Electrical and Computer Engineering Purdue University West Lafayette IN USA

Obtaining an optimal schedule for a set of precedence-constrained tasks with arbitrary costs is a well-known NP-complete problem. However, optimal solutions are desired in many situations. In this paper we propose search-based algorithms for determining optimal schedules for moderately large problem sizes. The first algorithm which is based on the A* search technique uses a computationally efficient cost function for guiding the search with reduced complexity. We propose a number of state-pruning techniques to reduce the size of the search space. For further lowering the complexity, we parallelize the search. The parallel version is based on reduced interprocessor communication and is guided by static and dynamic load-balancing schemes to evenly distribute the search states to the processors. We also propose an approximate algorithm that guarantees a bounded deviation from the optimal solution but takes considerably shorter time. Based on an extensive experimental evaluation of the algorithms, we conclude that the parallel algorithm with pruning techniques is an efficient scheme for generating optimal solutions for medium to moderately large problems while the approximate algorithm is a useful alternative if slightly degraded solutions are acceptable.

关键词： Optimal scheduling Processor scheduling Computational efficiency Costs Concurrent computing Network topology Scheduling algorithm Computer science Laboratories Multiprocessor interconnection networks

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：