检索结果-内蒙古大学图书馆

International Conference on Computer and Information Technology (CIT)

作者： Jing Zhou Yijie Wang Sikun Li National Key Laboratory for Parallel and Distributed School of Computer Science National University of Defense Technology China

Data replication introduces well-known consistency issues. This paper puts forward the question about data dependence in data consistency, which embodies pseudo-conflict updates and update dependency. According to that, an optimistic data consistency method is proposed. In our method, data object is partitioned into data blocks by fixed size, as the basic unit of data management. Updates are compressed by Bloom filter technique and propagated in double-path. Negotiation algorithms detect and reconcile update conflicts, and dynamic data management algorithms accommodate dynamic data processing. The results of the performance evaluation show that our method is an efficient method to achieve consistency, good dynamic property, and strong robustness.

关键词： Optimization methods Filters Partitioning algorithms Laboratories distributed processing Computer science Object detection Data analysis Heuristic algorithms Data processing

来源：评论

学校读者我要写书评

暂无评论

Graphcs: Graph-Based Client Selection for Heterogeneity in Federated Learning

SSRN

引用

SSRN 2022年

作者： Chang, Tao Li, Li Wu, MeiHan Yu, Wei Wang, Xiaodong Xu, ChengZhong Key Laboratory of Parallel and Distributed Computing College of Computer National University of Defense Technology China State Key Laboratory of Internet of Things for Smart City University of Macau China

Federated Learning coordinates many mobile devices to train an artificial intelligence model while preserving data privacy collaboratively. Mobile devices are usually equipped with totally different hardware configurations, leading to various training capabilities. At the same time, the distribution of the local training data is highly heterogeneous across different clients. Randomly selecting the clients to participate in the training process results in poor model performance and low system efficiency. In this paper, we propose GraphCS, a graph-based client selection framework for heterogeneity in Federated Learning. GraphCS first measures the distribution coupling across the clients via the model gradients. After that, it divides the clients into different groups according to the diversity of the local datasets. At the same time, it well estimates the runtime training capability of each client by jointly considering the hardware configuration and resource contention caused by the concurrently running *** the distribution coupling information and runtime training capability, GraphCS selects the \emph{right} clients in order to well balance the model accuracy and overall training progress. We evaluate the performance of GraphCS with mobile devices with different hardware configurations on various datasets. The experiment results show that our approach improves model accuracy up to 45.69%. Meanwhile, it reduces communication and computation overhead 87.35% and 89.48% at best, respectively. Furthermore, GraphCS accelerates the overall training process up to 35X. © 2022, The Authors. All rights reserved.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Agent oriented programming based on SLABS

Agent oriented programming based on SLABS

引用

IEEE Annual International Computer Software and Applications Conference (COMPSAC)

作者： Ji Wang Rui Shen Hong Zhu National Laboratory for Parallel and Distributed Processing Changsha China Department of Computing Oxford Brookes University Oxford UK

SLABS is a formal specification language designed for modular and composable specification of multi-agent systems. This paper reports our attempts to support SLABS at the level of programming languages. A programming language, SLABSp, is presented to support two distinguished mechanisms, namely caste and scenario, in caste-centric methodology of agent-oriented software development. Based on Java platform, the SLABSp has been implemented by compiling the programs into Java with the multi-agent runtime environment.

关键词： Slabs Computer languages Multiagent systems Programming Java Formal specifications Application software Protocols Laboratories distributed processing

来源：评论

学校读者我要写书评

暂无评论

Fascinating Supervisory Signals and Where to Find Them: Deep Anomaly Detection with Scale Learning

arXiv

引用

arXiv 2023年

作者： Xu, Hongzuo Wang, Yijie Wei, Juhui Jian, Songlei Li, Yizhou Liu, Ning National Key Laboratory of Parallel and Distributed Computing China College of Computer National University of Defense Technology China College of Science National University of Defense Technology China

Due to the unsupervised nature of anomaly detection, the key to fueling deep models is finding supervisory signals. Different from current reconstruction-guided generative models and transformation-based contrastive models, we devise novel data-driven supervision for tabular data by introducing a characteristic – scale – as data labels. By representing varied sub-vectors of data instances, we define scale as the relationship between the dimensionality of original sub-vectors and that of representations. Scales serve as labels attached to transformed representations, thus offering ample labeled data for neural network training. This paper further proposes a scale learning-based anomaly detection method. Supervised by the learning objective of scale distribution alignment, our approach learns the ranking of representations converted from varied subspaces of each data instance. Through this proxy task, our approach models inherent regularities and patterns within data, which well describes data "normality". Abnormal degrees of testing instances are obtained by measuring whether they fit these learned patterns. Extensive experiments show that our approach leads to significant improvement over state-of-the-art generative/contrastive anomaly detection methods. © 2023, CC BY.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

IWFR:Exploiting Full-duplex in Wireless Relay Networks

IWFR:Exploiting Full-duplex in Wireless Relay Networks

引用

2014 4th IEEE International Conference on Information Science and Technology

作者： Yong Lu Shaohe Lv Xiaodong Wang Xingming Zhou National Key Laboratory for Parallel and Distributed Processing School of Computer Science National University of Defense Technology

Traditional wireless relay networks have large endto-end time delay and low throughput because of the limit that it can't receive and forward at the same *** this paper,we proposed IWFR:Immediate Wireless Full-Duplex Relay which exploits the advantages of full-duplex to shorten the end-to-end time delay and improve the *** the same time,we designed a new implicit acknowledgement mechanism,which can eliminate the ACK overheads and evidently improve the throughput of the *** implement IWFR,we also modified the full-duplex node architecture to make it support for immediate *** shows that IWFR shortens the end-to-end time delay by 60%on average and improves the throughput to 240%of the original relay.

关键词： Relay IWFR:Exploiting Full-duplex in Wireless Relay Networks

来源：评论

学校读者我要写书评

暂无评论

An experimental study of the emergent behaviors of self-organized agent communities

An experimental study of the emergent behaviors of self-orga...

引用

Congress on Evolutionary Computation

作者： Shufeng Wang Hong Zhu National Laboratory for Parallel and Distributed Processing Changsha China Department of Computing Oxford Brookes University Oxford UK

Emergent behavior is an essential feature in multi-agent systems and plays a significant role in the applications of agent technology. Because of the huge gap between individual agents' behaviors and those of the whole system, specifying and reasoning about emergent behaviors are notoriously difficult. Simulation has been the essential method to study emergent behaviors in multi-agent systems. In this paper, we report an experimental study of the emergent behaviors of self-organized agent communities, in which emergent behaviors play a crucial role. The experiments confirmed the results of a theoretical analysis of agent communities using a formal theory called scenario calculus. It further provided insight into the dynamic features of the system that were very difficult to obtain by using formal logic, such as the speed of convergence to the emergent states and the relationships between the convergence time and various parameters of self-organized agent communities systems.

关键词： Evolutionary computation

来源：评论

学校读者我要写书评

暂无评论

Don't Half-listen: Capturing key-part Information in Continual Instruction Tuning

arXiv

引用

arXiv 2024年

作者： He, Yongquan Huang, Xuancheng Tang, Minghao Meng, Lingxun Li, Xiang Lin, Wei Zhang, Wenyuan Gao, Yifu Meituan China Institute of Information Engineering Chinese Academy of Sciences China National Key Laboratory of Parallel and Distributed Computing National University of Defense Technology China

Instruction tuning for large language models (LLMs) can drive them to produce results consistent with human goals in specific downstream tasks. However, the process of continual instruction tuning (CIT) for LLMs may bring about the catastrophic forgetting (CF) problem, where previously learned abilities are degraded. Recent methods try to alleviate the CF problem by modifying models or replaying data, which may only remember the surface-level pattern of instructions and get confused on held-out tasks. In this paper, we propose a novel continual instruction tuning method based on key-part Information Gain (KPIG). Our method computes the information gain on masked parts to dynamically replay data and refine the training objective, which enables LLMs to capture task-aware information relevant to the correct response and alleviate overfitting to general descriptions in instructions. In addition, we propose two metrics, P-score and V-score, to measure the generalization and instruction-following abilities of LLMs. Experiments demonstrate our method achieves superior performance on both seen and held-out tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

HyperSpring: Accurate and Stable Latency Estimation in the Hyperbolic Space

HyperSpring: Accurate and Stable Latency Estimation in the H...

引用

International Conference on parallel and distributed Systems (ICPADS)

作者： Yongquan Fu Yijie Wang National Key Laboratory of Parallel and Distributed Processing School of Computer National University of Defense Technology China

Predicting network latencies between Internet hosts can efficiently support large-scale Internet applications, e.g., file sharing service and the overlay construction. Several study use the hyperbolic space to model the Internet dense-core and many-tendril structure. However, existing hyperbolic space based embedding approaches are not designed for accurate latency estimation in the distributed context. We present HyperSpring, which estimates latency by modelling a mass spring system in the hyperbolic similar with Vivaldi. HyperSpring adopts coordinate initialization to speed up the convergence of coordinate computation, uses multiple-round symmetric updates to escape from bad local minima, and stabilizes coordinates by compensating RTT measurements to reduce the coordinate drifts. Evaluation results based on a network trace of 226 PlanetLab nodes indicate that, compared to Euclidean-space based Vivaldi, hyperspring provides performance improvements for most nodes, and incurs slightly higher distortions for a small number of nodes.

关键词： Delay IP networks Web and internet services Large-scale systems Peer to peer computing Springs Convergence Coordinate measuring machines Distortion measurement Extraterrestrial measurements

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 37

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

引用

37th Chinese Control Conference, CCC 2018

作者： Zheng, Guoxian Zhang, Lei Zhang, Huaxi Yulin Ding, Bo State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China MIS INSSET Universite de Picardie Jules Verne Amiens80039 France National Laboratory for Parallel and Distributed Processing National University of Defense Technology Changsha410008 China

ISBN: (纸本)9789881563941

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. © 2018 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Scenario mechanism in agent-oriented programming

Scenario mechanism in agent-oriented programming

引用

Asia-Pacific Conference on Software Engineering

作者： Rui Shen Ji Wang H. Zhu National Laboratory for Parallel and Distributed Processing Changsha China Department of Computing Oxford Brookes University Oxford UK

Scenario has been used to describe agent behaviors in the context of environment situations in the specification languages for agent-based systems, such as SLABS. It becomes an important language facility in the declaration of an agent for specifying its behaviors in its environment. Therefore, towards agent-oriented programming, it is necessary to introduce and implement scenario mechanism in programming languages. This paper reports our attempts to support the language facility from the view of programming languages, and presents an approach to facilitating the scenario mechanism in agent-oriented programming. The basic idea is to extend object-oriented programming language to support agent-oriented programming, where Java is chosen as the base language. Firstly, the language framework of agent-oriented programming, SLABSp is presented, mostly conforming to SLABS, whose syntax is extended based on Java. Scenario mechanism is introduced as the new feature in the programming language. Secondly, the underlying object models are defined to serve as the semantics of the language, where agents are modeled by a couple of objects. A compiler has been built to compile the agent-oriented programs into Java. A running platform has been constructed as the multiagent runtime environment of SLABSp.

关键词： Slabs Computer languages Java Object oriented modeling Object oriented programming Multiagent systems Specification languages Program processors Runtime environment Formal specifications

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：