检索结果-内蒙古大学图书馆

Find truth in the hands of the few:acquiring specific knowledge with crowdsourcing

Frontiers of Computer Science 2021年第4期15卷 5-16页

作者： Tao HAN Hailong SUN Yangqiu SONG Yili FANG Xudong LIU SKLSDE Lab School of Computer Science and EngineeringBeihang UniversityBeijing 100191China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang UniversityBeijing 100191China Department of Computer Science and Engineering Hong Kong University of Science and TechnologyClearwater BayHong Kong 999077China School of Computer and Information Engineering Zhejiang Gongshang UniversityHangzhou 310018China

Crowdsourcing has been a helpful mechanism to leverage human intelligence to acquire useful ***,when we aggregate the crowd knowledge based on the currently developed voting algorithms,it often results in common knowledge that may not be *** this paper,we consider the problem of collecting specific knowledge via *** the help of using external knowledge base such as WordNet,we incorporate the semantic relations between the alternative answers into a probabilisticmodel to determine which answer is more *** formulate the probabilistic model considering both worker’s ability and task’s difficulty from the basic assumption,and solve it by the expectation-maximization(EM)*** increase algorithm compatibility,we also refine our method into semi-supervised *** results show that our approach is robust with hyper-parameters and achieves better improvement thanmajority voting and other algorithms when more specific answers are expected,especially for sparse data.

关键词： crowdsourcing knowledge acquisition EM algorithm label aggregation

来源：评论

学校读者我要写书评

暂无评论

Patching Weak Convolutional Neural Network Models through Modularization and Composition

arXiv

引用

arXiv 2022年

作者： Qi, Binhang Sun, Hailong Gao, Xiang Zhang, Hongyu SKLSDE Lab Beihang University China The University of Newcastle Australia Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China

Despite great success in many applications, deep neural networks are not always robust in practice. For instance, a convolutional neuron network (CNN) model for classification tasks often performs unsatisfactorily in classifying some particular classes of objects. In this work, we are concerned with patching the weak part of a CNN model instead of improving it through the costly retraining of the entire model. Inspired by the fundamental concepts of modularization and composition in software engineering, we propose a compressed modularization approach, CNNSplitter, which decomposes a strong CNN model for N-class classification into N smaller CNN modules. Each module is a sub-model containing a part of the convolution kernels of the strong model. To patch a weak CNN model that performs unsatisfactorily on a target class (TC), we compose the weak CNN model with the corresponding module obtained from a strong CNN model. The ability of the weak CNN model to recognize the TC can thus be improved through patching. Moreover, the ability to recognize non-TCs is also improved, as the samples misclassified as TC could be classified as non-TCs correctly. Experimental results with two representative CNNs on three widely-used datasets show that the averaged improvement on the TC in terms of precision and recall are 12.54% and 2.14%, respectively. Moreover, patching improves the accuracy of non-TCs by 1.18%. The results demonstrate that CNNSplitter can patch a weak CNN model through modularization and composition, thus providing a new solution for developing robust CNN models. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

HiGIL: Hierarchical Graph Inference Learning for Fact Checking

HiGIL: Hierarchical Graph Inference Learning for Fact Checki...

引用

IEEE International Conference on data Mining (ICDM)

作者： Qianren Mao Yiming Wang Chenghong Yang Linfeng Du Hao Peng Jia Wu Jianxin Li Zheng Wang Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China Zhongguancun Laboratory Beijing China Department of Computing Macquarie University Sydney Australia The School of Computing University of Leeds Leeds U.K.

Fact-checking is vital for countering fake news. This process requires verifying the truthfulness of a claim by reasoning about multiple pieces of evidence. The current dominant approach depends upon capturing the claim-evidence relations from a claim-evidence interaction graph. Existing solutions utilize phrase-level semantics on a single-granularity but ignore other hierarchical features, such as fact- and sentence-level textual semantics and their logical topology. Since the hierarchical features often provide hints to infer collaborative high-order clues that can be essential for fact-checking, they should not be overlooked. This paper proposes a better method to model the claim-evidence graph in a multi-granularity manner. Doing so allows one to exploit more textual semantics and logical topology between a claim and its evidence. To achieve the target, we first employ a graph inference learning framework to infer graph nodes on different granular semantic units within their hierarchical topology. Then, an inference learning procedure is designed to optimize the global textual similarity and local topological reachability from the claim-evidence graph. We evaluate our approach by applying it to fact-checking on an open dataset, and experimental results show that our technique outperforms existing graph-based techniques by a large margin.

关键词： Semantics Collaboration Information retrieval Cognition Topology data mining Usability

来源：评论

学校读者我要写书评

暂无评论

Poincaré Differential Privacy for Hierarchy-Aware Graph Embedding

arXiv

引用

arXiv 2023年

作者： Wei, Yuecen Yuan, Haonan Fu, Xingcheng Sun, Qingyun Peng, Hao Li, Xianxian Hu, Chunming Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China School of Software Beihang University Beijing China Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University China

Hierarchy is an important and commonly observed topological property in real-world graphs that indicate the relationships between supervisors and subordinates or the organizational behavior of human groups. As hierarchy is introduced as a new inductive bias into the Graph Neural Networks (GNNs) in various tasks, it implies latent topological relations for attackers to improve their inference attack performance, leading to serious privacy leakage issues. In addition, existing privacy-preserving frameworks suffer from reduced protection ability in hierarchical propagation due to the deficiency of adaptive upper-bound estimation of the hierarchical perturbation boundary. It is of great urgency to effectively leverage the hierarchical property of data while satisfying privacy guarantees. To solve the problem, we propose the Poincaré Differential Privacy framework, named PoinDP, to protect the hierarchy-aware graph embedding based on hyperbolic geometry. Specifically, PoinDP first learns the hierarchy weights for each entity based on the Poincaré model in hyperbolic space. Then, the Personalized Hierarchy-aware Sensitivity is designed to measure the sensitivity of the hierarchical structure and adaptively allocate the privacy protection strength. Besides, the Hyperbolic Gaussian Mechanism (HGM) is proposed to extend the Gaussian mechanism in Euclidean space to hyperbolic space to realize random perturbations that satisfy differential privacy under the hyperbolic space metric. Extensive experiment results on five real-world datasets demonstrate the proposed PoinDP's advantages of effective privacy protection while maintaining good performance on the node classification task. Copyright © 2023, The Authors. All rights reserved.

关键词： Backpropagation

来源：评论

学校读者我要写书评

暂无评论

Last-X-Generation Archiving Strategy for Multi-Objective Evolutionary Algorithms

Last-X-Generation Archiving Strategy for Multi-Objective Evo...

引用

Congress on Evolutionary Computation

作者： Tianye Shu Yang Nan Ke Shang Hisao Ishibuchi Department of Computer Science and Engineering Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Southern University of Science and Technology Shenzhen China Southern University of Science and Technology Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China

ISBN: (数字)9798350308365

ISBN: (纸本)9798350308372

For evolutionary multi-objective optimization algorithms (EMOAs), an external archive can be utilized for saving good solutions found throughout the evolutionary process. Recent studies showed that a solution set selected from an external archive is usually superior to the final population. That is, the incorporation of an external archive improves the performance of EMOAs. However, the computation time for maintaining an external archive is long, especially when the archive size is large. To solve this issue, a simple archiving strategy is to save all solutions generated in the last several generations. In this paper, we examine this archiving strategy for three representative EMOAs on artificial test problems (Minus-DTLZ and WFG) and real-world problems (RE). Our results show that archiving the last several generations clearly improves the performance of EMOAs without severely increasing the computation time.

关键词： Costs Sociology Evolutionary computation Statistics Optimization Standards

来源：评论

学校读者我要写书评

暂无评论

An Improvement of the Rational Representation for High-Dimensional Systems

引用

Journal of Systems Science & Complexity 2021年第6期34卷 2410-2427页

作者： XIAO Fanghui LU Dong MA Xiaodong WANG Dingkang KLMM Academy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190China School of Mathematical Sciences University of Chinese Academy of SciencesBeijing 100049China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang UniversityBeijing 100191China School of Mathematical Sciences Beihang UniversityBeijing 100191China College of Science China Agricultural UniversityBeijing 100083China

Based on the rational univariate representation of zero-dimensional polynomial systems,Tan and Zhang proposed the rational representation theory for solving a high-dimensional polynomial system,which uses so-called rational representation sets to describe all the zeros of a high-dimensional polynomial *** paper is devoted to giving an improvement for the rational *** idea of this improvement comes from a minimal Dickson basis used for computing a comprehensive Grobner system of a parametric polynomial system to reduce the number of *** authors replace the normal Grobner basis G satisfying certain conditions in the original algorithm(Tan-Zhang’s algorithm)with a minimal Dickson basis G_(m) of a Grobner basis for the ideal,where G_(m) is smaller in size than *** on this,the authors give an improved ***,the proposed algorithm has been implemented on the computer algebra system *** data and its performance comparison with the original algorithm show that it generates fewer branches and the improvement is rewarding.

关键词： Comprehensive Grobner systems high-dimensional polynomial system rational representation rational univariate representation

来源：评论

学校读者我要写书评

暂无评论

Motion Forecasting for Autonomous Vehicles: A Survey

arXiv

引用

arXiv 2025年

作者： Shi, Jianxin Chen, Jinhao Wang, Yuandong Sun, Li Liu, Chunyang Xiong, Wei Wo, Tianyu Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China Information Engineering College Capital Normal University Beijing100048 China School of Control and Computer Engineering North China Electric Power University Beijing102206 China Didi Chuxing Beijing100094 China

In recent years, the field of autonomous driving has attracted increasingly significant public interest. Accurately forecasting the future behavior of various traffic participants is essential for the decision-making of Autonomous Vehicles (AVs). In this paper, we focus on both scenario-based and perception-based motion forecasting for AVs. We propose a formal problem formulation for motion forecasting and summarize the main challenges confronting this area of research. We also detail representative datasets and evaluation metrics pertinent to this field. Furthermore, this study classifies recent research into two main categories: supervised learning and self-supervised learning, reflecting the evolving paradigms in both scenario-based and perception-based motion forecasting. In the context of supervised learning, we thoroughly examine and analyze each key element of the methodology. For self-supervised learning, we summarize commonly adopted techniques. The paper concludes and discusses potential research directions, aiming to propel progress in this vital area of AV technology. © 2025, CC BY.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Real-time partitioned scheduling: Exploiting the inter-resource affinity for task allocation on multiprocessors

Real-time partitioned scheduling: Exploiting the inter-resou...

引用

作者： Akram, Naveed Li, Jianxin Bai, Yan Zhang, Yangyang Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China School of Engineering and Technology University of Washington Tacoma WA United States

Real-time edge computing is forging its place in cloud computing rapidly, and requirements for high-performance edge devices are becoming increasingly complex. Multiprocessor edge devices are an attractive choice to meet these higher performance requirements. However, multiprocessor devices encounter inherent challenges when handling on-chip shared resources. The concurrent access to these resources by the tasks requesting more than one shared resource and running on multiple processors may face huge blocking times, which can lead to missed hard real-time deadlines and cause a catastrophic system failure. To reduce the task blocking time, we propose a task allocation algorithm that takes advantage of inter-resource affinity and allocates all the tasks accessing multiple shared resources having inter-resource affinity on the same processor of the multiprocessor. The proposed algorithm reduces global resources and remote blocking, which subsequently increase schedulability of task sets and reduce the processor utilization. In our experiments, we compare the proposed task allocation algorithm SRTA with existing well-known task allocation strategies SPA, ROP, and blocking-agnostic FFD. The experimental results reveal that the SRTA, on the average, can allocate 1.80, 2.34, and 3.14 times more task sets as compared to ROP, SPA, and FFD, respectively and reduces the number of globally shared resources significantly. © 2019 John Wiley & Sons, Ltd.

关键词： Scheduling

来源：评论

学校读者我要写书评

暂无评论

data-Driven Control Based on Function Approximation with Binomial Coefficients

Data-Driven Control Based on Function Approximation with Bin...

引用

第33届中国控制与决策会议

作者： Guoliang Zhu Lei Chen Kexin Liu Jinhu Lü School of Automation Science and Electrical Engineering Beihang Uniersity Advanced Research Institute of Multidisciplinary Science Beijing Institute of Technology Advanced Innovation Center for Big Data and Brain Computing Beihang University

This paper investigates data-driven control methods based on function approximation with binomial coefficients and sampling *** propose two approximate models and corresponding controllers formed from sampled *** shows that the information truncated in the first approximate model is saved in the latter with parameter estimation *** results validate the effectiveness of proposed approaches.

关键词： Sampled-data driven systems Function approximation Approximate theory Adaptive control Binomial coefficients

来源：评论

学校读者我要写书评

暂无评论

An Agent-Based Approach for Time-Series Momentum and Reversal

引用

Journal of Systems Science & Complexity 2020年第2期33卷 461-474页

作者： WANG Zhaoyuan LIU Shancun YANG Haijun WU Harris School of Economics and Management Beihang UniversityBeijing 100191China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang UniversityBeijing 100191China College of Business and Public Administration Old Dominion UniversityNorfolkVirginiaUSA

This paper proposes a novel agent-based model combining private information diffusion to explain time-series momentum and *** information transmission allows heterogeneous trading strategies coexist in the artificial *** experiments reproduce momentum in short horizon and reversal in long horizon in the artificial financial ***,the authors also analyze how the private information contagion affects the ***,the authors find the significant price trend and excess volatility of volume when private information diffuses gradually.

关键词： Agent-based model excess volatility of volume price trend private information contagion time-series momentum

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：