检索结果-内蒙古大学图书馆

Residual diverse ensemble for long-tailed multi-label text classification

Science China(Information Sciences) 2024年第11期67卷 92-105页

作者： Jiangxin SHI Tong WEI Yufeng LI National Key Laboratory for Novel Software Technology Nanjing University School of Artificial Intelligence Nanjing University School of Computer Science and Engineering Southeast University Key Laboratory of Computer Network and Information Integration Southeast UniversityMinistry of Education

Long-tailed multi-label text classification aims to identify a subset of relevant labels from a large candidate label set, where the training datasets usually follow long-tailed label distributions. Many of the previous studies have treated head and tail labels equally, resulting in unsatisfactory performance for identifying tail labels. To address this issue, this paper proposes a novel learning method that combines arbitrary models with two steps. The first step is the “diverse ensemble” that encourages diverse predictions among multiple shallow classifiers, particularly on tail labels, and can improve the generalization of tail *** second is the “error correction” that takes advantage of accurate predictions on head labels by the base model and approximates its residual errors for tail labels. Thus, it enables the “diverse ensemble” to focus on optimizing the tail label performance. This overall procedure is called residual diverse ensemble(RDE). RDE is implemented via a single-hidden-layer perceptron and can be used for scaling up to hundreds of thousands of labels. We empirically show that RDE consistently improves many existing models with considerable performance gains on benchmark datasets, especially with respect to the propensity-scored evaluation ***, RDE converges in less than 30 training epochs without increasing the computational overhead.

关键词： multi-label learning extreme multi-label learning long-tailed distribution multi-label text classification ensemble learning

来源：评论

学校读者我要写书评

暂无评论

Development of DNA computing and information processing based on DNA-strand displacement

引用

Science China Chemistry 2015年第10期58卷 1515-1523页

作者： Yafei Dong Chen Dong Fei Wan Jing Yang Cheng Zhang College of Life Science Shaanxi Normal University School of Control and Computer Engineering North China Electric Power University Key Laboratory of High Confidence Software Technologies of Ministry of Education Software Engineering Institute School of Electronics Engineering and Computer Science Peking University

DNA computing, currently a hot research field in information processing, has the advantages of parallelism, low energy consumption, and high storability, therefore, it has been applied to a variety of complicated computational problems. The emerging field of DNA nanotechnology has also developed quickly; within it, the method of DNA strand displacement has drawn great attention because it is self-induced, sensitive, accurate, and operationally simple. This article summarizes five aspects of the recent developments of DNA-strand displacement in DNA computing:(1) cascading circuits;(2) catalyzed reaction;(3) logic computation;(4) DNA computing on surfaces; and(5) logic computing based on nanoparticles guided by strand displacement. The applications and mechanisms of strand displacement in DNA computing are discussed and possible future developments are presented.

关键词： DNA computing information processing strand displacement self-assembly nanomaterial

来源：评论

学校读者我要写书评

暂无评论

A Novel Hardware/software Partitioning Method Based on Position Disturbed Particle Swarm Optimization with Invasive Weed Optimization

引用

Journal of computer Science & Technology 2017年第2期32卷 340-355页

作者： Xiao-Hu Yan Fa-Zhi He Yi-Lin Chen State Key Laboratory of Software Engineering Wuhan University Wuhan 430072 China School of Computer Science Wuhan University Wuhan 430072 China

With the development of the design complexity in embedded systems, hardware/software （HW/SW） partitioning becomes a challenging optimization problem in HW/SW co-design. A novel HW/SW partitioning method based on position disturbed particle swarm optimization with invasive weed optimization （PDPSO-IWO） is presented in this paper. It is found by biologists that the ground squirrels produce alarm calls which warn their peers to move away when there is potential predatory threat. Here, we present PDPSO algorithm, in each iteration of which the squirrel behavior of escaping from the global worst particle can be simulated to increase population diversity and avoid local optimum. We also present new initialization and reproduction strategies to improve IWO algorithm for searching a better position, with which the global best position can be updated. Then the search accuracy and the solution quality can be enhanced. PDPSO and improved IWO are synthesized into one single PDPSO-IWO algorithm, which can keep both searching diversification and searching intensification. Furthermore, a hybrid NodeRank （HNodeRank） algorithm is proposed to initialize the population of PDPSO-IWO, and the solution quality can be enhanced further. Since the HW/SW communication cost computing is the most time-consuming process for HW/SW partitioning algorithm, we adopt the GPU parallel technique to accelerate the computing. In this way, the runtime of PDPSO-IWO for large-scale HW/SW partitioning problem can be reduced efficiently. Finally, multiple experiments on benchmarks from state-of-the-art publications and large-scale HW/SW partitioning demonstrate that the proposed algorithm can achieve higher performance than other algorithms.

关键词： hardware/software partitioning particle swarm optimization invasive weed optimization communicationcost parallel computing

来源：评论

学校读者我要写书评

暂无评论

swSpAMM:optimizing large-scale sparse approximate matrix multiplication on Sunway Taihulight

引用

Frontiers of computer Science 2023年第4期17卷 29-41页

作者： Xiaoyan LIU Yi LIU Bohong YIN Hailong YANG Zhongzhi LUAN Depei QIAN State Key Laboratory of Software Development Environment Beijing 100191China School of Computer Science and Engineering Beihang UniversityBeijing 100191China

Although matrix multiplication plays an essential role in a wide range of applications,previous works only focus on optimizing dense or sparse matrix *** Sparse Approximate Matrix Multiply(SpAMM)is an algorithm to accelerate the multiplication of decay matrices,the sparsity of which is between dense and sparse *** addition,large-scale decay matrix multiplication is performed in scientific applications to solve cutting-edge *** optimize large-scale decay matrix multiplication using SpAMM on supercomputers such as Sunway Taihulight,we present swSpAMM,an optimized SpAMM algorithm by adapting the computation characteristics to the architecture features of Sunway ***,we propose both intra-node and inter-node optimizations to accelerate swSpAMM for large-scale *** intra-node optimizations,we explore algorithm parallelization and block-major data layout that are tailored to better utilize the architecture advantage of Sunway *** inter-node optimizations,we propose a matrix organization strategy for better distributing sub-matrices across nodes and a dynamic scheduling strategy for improving load balance across *** compare swSpAMM with the existing GEMM library on a single node as well as large-scale matrix multiplication methods on multiple *** experiment results show that swSpAMM achieves a speedup up to 14.5×and 2.2×when compared to xMath library on a single node and 2D GEMM method on multiple nodes,respectively.

关键词： approximate calculation sunway processor performance optimization

来源：评论

学校读者我要写书评

暂无评论

Towards architecture-based management of platforms in the cloud

引用

Frontiers of computer Science 2012年第4期6卷 388-397页

作者： Gang HUANG Xing CHEN Ying ZHANG Xiaodong ZHANG Key Laboratory of High Confidence Software Technologies(Ministry of Education) School of Electronics Engineering and Computer SciencePeking UniversityBeijing 100871China

System management is becoming increasingly complex and brings high costs, especially with the advent of cloud computing. Cloud computing involves numerous platforms often of virtual machines （VMs） and middleware has to be managed to make the whole system work cost- effectively after an application is deployed. In order to re- duce management costs, in particular for the manual activi- ties, many computer programs have been developed remove or reduce the complexity and difficulty of system mamnage- ment. These programs are usually hard-coded in languages like Java and C＋＋, which bring enough capability and flexi- bility but also cause high programming effort and cost. This paper proposes an architecture for developing management programs in a simple but powerful way. First of all, the man- ageability of a given platform （via APIs, configuration files, and scripts） is abstracted as a runtime model of the plat- form＇s software architecture, which can automatically and immediately propagate any observable runtime changes of the target platforms to the corresponding architecture mod- els, and vice versa. The management programs are devel- oped using modeling languages, instead of those relatively low-level programming languages. Architecture-level man- agement programs bring many advantages related to perfor- mance, interoperability, reusability, and simplicity. An experiment on a real-world cloud deployment and comparison with traditional programming language approaches demonstrate the feasibility, effectiveness, and benefits of the new model based approach for management program development.

关键词： cloud management software architecture models at runtime

来源：评论

学校读者我要写书评

暂无评论

Building Modeling Tools Based on Metamodeling and Product Line Technologies

引用

Chinese Journal of Electronics 2014年第2期23卷 219-226页

作者： MA Zhiyi HE Xiao Software Institute School of Electronics Engineering and Computer Science Peking University Key Laboratory of High Confidence Software Technologies (Peking University) Ministry of Education School of Computer and Communication Engineering University of Science and Technology Beijing

With the evolution of existing modeling languages and the emergence of more and more new modeling languages, it is necessary to rapidly build the corresponding software modeling tools with good quality. However, modeling tools for larger modeling languages are usually diversity in function and complexity in implementation technology. Taking building modeling tools as a domain,this paper presents an approach to building software modeling tools based on metamodeling and product line technologies. The paper provides the concept system of the approach and a feature model from diverse functions of modeling tools in order to specify the commonality and variability of the tools by deeply making the domain analysis,discusses the design and implementation of a general tool framework that provides the conveniences for reusing components and generating code for components, and specifies the mapping between the feature model and the components for modeling tools.

关键词： software modeling tool Metamodeling software product line

来源：评论

学校读者我要写书评

暂无评论

A new model for model checking: cycle-weighted Kripke structure

引用

中国高等学校学术文摘·计算机科学 2010年第1期4卷 78-88页

作者： Jiaqi ZHU Hanpin WANG Zhongyuan XU Chunxiang XU Key Laboratory of High Confidence Software Technologies Ministry of Education School of Electronic Engineering and Computer SciencePeking UniversityBeijing 100871China

This paper proposes a new model, named cycle-weighted Kripke structure (CWKS), based on the traditional Kripke structure. It adds two integer weights to some transitions of the Kripke structure, restricting when these transitions can occur. These weights mainly specify the occurrences of some cycles in a Kripke structure, giving a range of how many times these cycles may be executed repeatedly. This new model can efficiently describe some quantitative discrete-time characters of reactive and concurrent systems, so it is significant for some model checking problems. We also define a subset of CWKS, named conditional CWKS, which satisfies a constraint referring to the weighted transitions in the structure. The paper modifies the explicit computation tree logic (CTL) model checking algorithm to accommodate the conditional CWKS. It can also be regarded as the foundation of some more complex models obtained by extending from the Kripke structure, which will be studied in the future.

关键词： model checking Kripke structure weighted cycles computation tree logic (CTL)

来源：评论

学校读者我要写书评

暂无评论

Challenges and countermeasures of interaction in autonomous vehicles

引用

Science China(Information Sciences) 2019年第5期62卷 5-7页

作者： Deyi LI Meng LIU Fei ZHAO Yu LIU State Key Laboratory of Software Development Environment School of Computer Science and EngineeringBeihang University Chinese Academy of Engineering School of Transportation Science and Engineering Beihang University

Autonomous vehicles can bring changes into ways of traveling, traffic, and even production modes [1].At present, the majority of researches [2] on autonomous vehicles are limited in perception, planning, decision-making and other calculation front,while interactive cognitive perspective is barely looked into. The interactive sector involved in self-driving is rather sophisticated [3]. However,

关键词： Challenges and countermeasures of interaction in autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Generalized Cross-Entropy Benchmarking for Random Circuits with Ergodicity

arXiv

引用

arXiv 2025年

作者： Cheng, Bin Meng, Fei Zhang, Zhi-Jiong Yung, Man-Hong Shenzhen Institute for Quantum Science and Engineering Department of Physics Southern University of Science and Technology Shenzhen518055 China Centre for Quantum Technologies National University of Singapore Singapore Centre for Quantum Software and Information Faculty of Engineering and Information Technology University of Technology SydneyNSW2007 Australia Department of Physics City University of Hong Kong Tat Chee Avenue Kowloon Hong Kong QICI Quantum Information and Computation Initiative Department of Computer Science The University of Hong Kong Pokfulam Road Hong Kong International Quantum Academy Shenzhen518048 China Guangdong Provincial Key Laboratory of Quantum Science and Engineering Southern University of Science and Technology Shenzhen518055 China Shenzhen Key Laboratory of Quantum Science and Engineering Southern University of Science and Technology Shenzhen518055 China

Cross-entropy benchmarking is a central technique used to certify a quantum chip in recent experiments. To better understand its mathematical foundation and develop new benchmarking schemes, we introduce the concept of ergodicity to random circuit sampling and find that the Haar random quantum circuit satisfies an ergodicity condition—the average of certain types of post-processing function over the output bit strings is close to the average over the unitary ensemble. For noiseless random circuits, we prove that the ergodicity holds for polynomials of degree t with positive coefficients and when the random circuits form a unitary 2t-design. For strong enough noise, the ergodicity condition is violated. This suggests that ergodicity is a property that can be exploited to certify a quantum chip. We formulate the deviation of ergodicity as a measure for quantum chip benchmarking and show that it can be used to estimate the circuit fidelity for global depolarizing noise and weakly correlated noise. For a quadratic post-processing function, our framework recovers Google’s result on estimating the circuit fidelity via linear cross-entropy benchmarking (XEB), and we give a sufficient condition on the noise model characterizing when such estimation is valid. Our results establish an interesting connection between ergodicity and noise in random circuits and provide new insights into designing quantum benchmarking schemes. Copyright © 2025, The Authors. All rights reserved.

关键词： Quantum electronics

来源：评论

学校读者我要写书评

暂无评论

Hybrid Model Testing Technique for Deep-Sea Platforms Based on Equivalent Water Depth Truncation

引用

China Ocean engineering 2007年第3期21卷 401-416页

作者：张火明杨建民肖龙飞 School of Computer Software and Theory China Jiliang University The State Key Laboratory of Ocean Engineering Shanghai Jiao Tong University

In this paper, an inner turret moored FPSO which works in the water of 320 m depth, is selected to study the socalled ＂passively-truncated ＋ numerical-simulation＂ type of hybrid model testing technique while the tnmcated water depth is 160 m and the model scale ）, = 80. During the investigation, the optimization design of the equivalent-depth truncated system is performed by using the similarity of the static characteristics between the truncated system and the full depth one as the objective function. According to the truncated system, the corresponding physical test model is made. By adopting the coupling time domain simulation method, the tnmcated system model test is numerically reconstructed to carefully verify the computer simulation software and to adjust the corresponding hydrodynamic parameters. Based on the above work, the numerical extrapolation to the full depth system is performed by using the verified computer software and the adjusted hydrodyrmmic parameters. The full depth system model test is then performed in the basin and the results are compared with those from the numerical extrapolation. At last, the implementation procedure and the key technique of the hybrid model testing of the deep-sea platforms are summarized and printed. Through the above investigations, some beneficial conclusions are presented.

关键词： hybrid model testing technique equivalent water depth truncation FPSO hydrodynamic response turret

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：